uri.h File Reference

#include <stdio.h>
#include <libxml/xmlversion.h>
#include <libxml/xmlstring.h>

Include dependency graph for uri.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
struct	_xmlURI

Typedefs
typedef struct _xmlURI	xmlURI
typedef xmlURI *	xmlURIPtr

Functions
XMLPUBFUN xmlURIPtr	xmlCreateURI (void)
XMLPUBFUN xmlChar *	xmlBuildURI (const xmlChar *URI, const xmlChar *base)
XMLPUBFUN xmlChar *	xmlBuildRelativeURI (const xmlChar *URI, const xmlChar *base)
XMLPUBFUN xmlURIPtr	xmlParseURI (const char *str)
XMLPUBFUN xmlURIPtr	xmlParseURIRaw (const char *str, int raw)
XMLPUBFUN int	xmlParseURIReference (xmlURIPtr uri, const char *str)
XMLPUBFUN xmlChar *	xmlSaveUri (xmlURIPtr uri)
XMLPUBFUN void	xmlPrintURI (FILE *stream, xmlURIPtr uri)
XMLPUBFUN xmlChar *	xmlURIEscapeStr (const xmlChar *str, const xmlChar *list)
XMLPUBFUN char *	xmlURIUnescapeString (const char *str, int len, char *target)
XMLPUBFUN int	xmlNormalizeURIPath (char *path)
XMLPUBFUN xmlChar *	xmlURIEscape (const xmlChar *str)
XMLPUBFUN void	xmlFreeURI (xmlURIPtr uri)
XMLPUBFUN xmlChar *	xmlCanonicPath (const xmlChar *path)
XMLPUBFUN xmlChar *	xmlPathToURI (const xmlChar *path)

Typedef Documentation

xmlURI

typedef struct _xmlURI xmlURI

Summary: library of generic URI related routines Description: library of generic URI related routines Implements RFC 2396

Copy: See Copyright for the status of this software.

Author: Daniel Veillard xmlURI:

A parsed URI reference. This is a struct containing the various fields as described in RFC 2396 but separated for further processing.

Note: query is a deprecated field which is incorrectly unescaped. query_raw takes precedence over query if the former is set. See: http://mail.gnome.org/archives/xml/2007-April/thread.html#00127

Definition at line 32 of file uri.h.

xmlURIPtr

typedef xmlURI* xmlURIPtr

Definition at line 33 of file uri.h.

Function Documentation

xmlBuildRelativeURI()

XMLPUBFUN xmlChar * xmlBuildRelativeURI	(	const xmlChar *	URI,
		const xmlChar *	base
	)

xmlBuildRelativeURI: @URI: the URI reference under consideration @base: the base value

Expresses the URI of the reference in terms relative to the base. Some examples of this operation include: base = "http://site1.com/docs/book1.html" URI input URI returned docs/pic1.gif pic1.gif docs/img/pic1.gif img/pic1.gif img/pic1.gif ../img/pic1.gif http://site1.com/docs/pic1.gif pic1.gif http://site2.com/docs/pic1.gif http://site2.com/docs/pic1.gif

base = "docs/book1.html" URI input URI returned docs/pic1.gif pic1.gif docs/img/pic1.gif img/pic1.gif img/pic1.gif ../img/pic1.gif http://site1.com/docs/pic1.gif http://site1.com/docs/pic1.gif

Note: if the URI reference is really weird or complicated, it may be worthwhile to first convert it into a "nice" one by calling xmlBuildURI (using 'base') before calling this routine, since this routine (for reasonable efficiency) assumes URI has already been through some validation.

Returns a new URI string (to be freed by the caller) or NULL in case error.

Definition at line 2186 of file uri.c.

{
    xmlChar *val = NULL;
    int ret;
    int ix;
    int nbslash = 0;
    int len;
    xmlURIPtr ref = NULL;
    xmlURIPtr bas = NULL;
    xmlChar *bptr, *uptr, *vptr;
    int remove_path = 0;
 
    if ((URI == NULL) || (*URI == 0))
    return NULL;
 
    /*
     * First parse URI into a standard form
     */
    ref = xmlCreateURI ();
    if (ref == NULL)
    return NULL;
    /* If URI not already in "relative" form */
    if (URI[0] != '.') {
    ret = xmlParseURIReference (ref, (const char *) URI);
    if (ret != 0)
        goto done;      /* Error in URI, return NULL */
    } else
    ref->path = (char *)xmlStrdup(URI);
 
    /*
     * Next parse base into the same standard form
     */
    if ((base == NULL) || (*base == 0)) {
    val = xmlStrdup (URI);
    goto done;
    }
    bas = xmlCreateURI ();
    if (bas == NULL)
    goto done;
    if (base[0] != '.') {
    ret = xmlParseURIReference (bas, (const char *) base);
    if (ret != 0)
        goto done;      /* Error in base, return NULL */
    } else
    bas->path = (char *)xmlStrdup(base);
 
    /*
     * If the scheme / server on the URI differs from the base,
     * just return the URI
     */
    if ((ref->scheme != NULL) &&
    ((bas->scheme == NULL) ||
     (xmlStrcmp ((xmlChar *)bas->scheme, (xmlChar *)ref->scheme)) ||
     (xmlStrcmp ((xmlChar *)bas->server, (xmlChar *)ref->server)) ||
         (bas->port != ref->port))) {
    val = xmlStrdup (URI);
    goto done;
    }
    if (xmlStrEqual((xmlChar *)bas->path, (xmlChar *)ref->path)) {
    val = xmlStrdup(BAD_CAST "");
    goto done;
    }
    if (bas->path == NULL) {
    val = xmlStrdup((xmlChar *)ref->path);
    goto done;
    }
    if (ref->path == NULL) {
        ref->path = (char *) "/";
    remove_path = 1;
    }
 
    /*
     * At this point (at last!) we can compare the two paths
     *
     * First we take care of the special case where either of the
     * two path components may be missing (bug 316224)
     */
    bptr = (xmlChar *)bas->path;
    {
        xmlChar *rptr = (xmlChar *) ref->path;
        int pos = 0;
 
        /*
         * Next we compare the two strings and find where they first differ
         */
    if ((*rptr == '.') && (rptr[1] == '/'))
            rptr += 2;
    if ((*bptr == '.') && (bptr[1] == '/'))
            bptr += 2;
    else if ((*bptr == '/') && (*rptr != '/'))
        bptr++;
    while ((bptr[pos] == rptr[pos]) && (bptr[pos] != 0))
        pos++;
 
    if (bptr[pos] == rptr[pos]) {
        val = xmlStrdup(BAD_CAST "");
        goto done;      /* (I can't imagine why anyone would do this) */
    }
 
    /*
     * In URI, "back up" to the last '/' encountered.  This will be the
     * beginning of the "unique" suffix of URI
     */
    ix = pos;
    for (; ix > 0; ix--) {
        if (rptr[ix - 1] == '/')
        break;
    }
    uptr = (xmlChar *)&rptr[ix];
 
    /*
     * In base, count the number of '/' from the differing point
     */
    for (; bptr[ix] != 0; ix++) {
        if (bptr[ix] == '/')
        nbslash++;
    }
 
    /*
     * e.g: URI="foo/" base="foo/bar" -> "./"
     */
    if (nbslash == 0 && !uptr[0]) {
        val = xmlStrdup(BAD_CAST "./");
        goto done;
    }
 
    len = xmlStrlen (uptr) + 1;
    }
 
    if (nbslash == 0) {
    if (uptr != NULL)
        /* exception characters from xmlSaveUri */
        val = xmlURIEscapeStr(uptr, BAD_CAST "/;&=+$,");
    goto done;
    }
 
    /*
     * Allocate just enough space for the returned string -
     * length of the remainder of the URI, plus enough space
     * for the "../" groups, plus one for the terminator
     */
    val = (xmlChar *) xmlMalloc (len + 3 * nbslash);
    if (val == NULL) {
        xmlURIErrMemory("building relative URI\n");
    goto done;
    }
    vptr = val;
    /*
     * Put in as many "../" as needed
     */
    for (; nbslash>0; nbslash--) {
    *vptr++ = '.';
    *vptr++ = '.';
    *vptr++ = '/';
    }
    /*
     * Finish up with the end of the URI
     */
    if (uptr != NULL) {
        if ((vptr > val) && (len > 0) &&
        (uptr[0] == '/') && (vptr[-1] == '/')) {
        memcpy (vptr, uptr + 1, len - 1);
        vptr[len - 2] = 0;
    } else {
        memcpy (vptr, uptr, len);
        vptr[len - 1] = 0;
    }
    } else {
    vptr[len - 1] = 0;
    }
 
    /* escape the freshly-built path */
    vptr = val;
    /* exception characters from xmlSaveUri */
    val = xmlURIEscapeStr(vptr, BAD_CAST "/;&=+$,");
    xmlFree(vptr);
 
done:
    /*
     * Free the working variables
     */
    if (remove_path != 0)
        ref->path = NULL;
    if (ref != NULL)
    xmlFreeURI (ref);
    if (bas != NULL)
    xmlFreeURI (bas);
 
    return val;
}

xmlBuildURI()

XMLPUBFUN xmlChar * xmlBuildURI	(	const xmlChar *	URI,
		const xmlChar *	base
	)

xmlBuildURI: @URI: the URI instance found in the document @base: the base value

Computes he final URI of the reference done by checking that the given URI is valid, and building the final URI using the base URI. This is processed according to section 5.2 of the RFC 2396

5.2. Resolving Relative References to Absolute Form

Returns a new URI string (to be freed by the caller) or NULL in case of error.

Definition at line 1902 of file uri.c.

                                                     {
    xmlChar *val = NULL;
    int ret, len, indx, cur, out;
    xmlURIPtr ref = NULL;
    xmlURIPtr bas = NULL;
    xmlURIPtr res = NULL;
 
    /*
     * 1) The URI reference is parsed into the potential four components and
     *    fragment identifier, as described in Section 4.3.
     *
     *    NOTE that a completely empty URI is treated by modern browsers
     *    as a reference to "." rather than as a synonym for the current
     *    URI.  Should we do that here?
     */
    if (URI == NULL)
    ret = -1;
    else {
    if (*URI) {
        ref = xmlCreateURI();
        if (ref == NULL)
        goto done;
        ret = xmlParseURIReference(ref, (const char *) URI);
    }
    else
        ret = 0;
    }
    if (ret != 0)
    goto done;
    if ((ref != NULL) && (ref->scheme != NULL)) {
    /*
     * The URI is absolute don't modify.
     */
    val = xmlStrdup(URI);
    goto done;
    }
    if (base == NULL)
    ret = -1;
    else {
    bas = xmlCreateURI();
    if (bas == NULL)
        goto done;
    ret = xmlParseURIReference(bas, (const char *) base);
    }
    if (ret != 0) {
    if (ref)
        val = xmlSaveUri(ref);
    goto done;
    }
    if (ref == NULL) {
    /*
     * the base fragment must be ignored
     */
    if (bas->fragment != NULL) {
        xmlFree(bas->fragment);
        bas->fragment = NULL;
    }
    val = xmlSaveUri(bas);
    goto done;
    }
 
    /*
     * 2) If the path component is empty and the scheme, authority, and
     *    query components are undefined, then it is a reference to the
     *    current document and we are done.  Otherwise, the reference URI's
     *    query and fragment components are defined as found (or not found)
     *    within the URI reference and not inherited from the base URI.
     *
     *    NOTE that in modern browsers, the parsing differs from the above
     *    in the following aspect:  the query component is allowed to be
     *    defined while still treating this as a reference to the current
     *    document.
     */
    res = xmlCreateURI();
    if (res == NULL)
    goto done;
    if ((ref->scheme == NULL) && (ref->path == NULL) &&
    ((ref->authority == NULL) && (ref->server == NULL) &&
         (ref->port == PORT_EMPTY))) {
    if (bas->scheme != NULL)
        res->scheme = xmlMemStrdup(bas->scheme);
    if (bas->authority != NULL)
        res->authority = xmlMemStrdup(bas->authority);
    else {
        if (bas->server != NULL)
        res->server = xmlMemStrdup(bas->server);
        if (bas->user != NULL)
        res->user = xmlMemStrdup(bas->user);
        res->port = bas->port;
    }
    if (bas->path != NULL)
        res->path = xmlMemStrdup(bas->path);
    if (ref->query_raw != NULL)
        res->query_raw = xmlMemStrdup (ref->query_raw);
    else if (ref->query != NULL)
        res->query = xmlMemStrdup(ref->query);
    else if (bas->query_raw != NULL)
        res->query_raw = xmlMemStrdup(bas->query_raw);
    else if (bas->query != NULL)
        res->query = xmlMemStrdup(bas->query);
    if (ref->fragment != NULL)
        res->fragment = xmlMemStrdup(ref->fragment);
    goto step_7;
    }
 
    /*
     * 3) If the scheme component is defined, indicating that the reference
     *    starts with a scheme name, then the reference is interpreted as an
     *    absolute URI and we are done.  Otherwise, the reference URI's
     *    scheme is inherited from the base URI's scheme component.
     */
    if (ref->scheme != NULL) {
    val = xmlSaveUri(ref);
    goto done;
    }
    if (bas->scheme != NULL)
    res->scheme = xmlMemStrdup(bas->scheme);
 
    if (ref->query_raw != NULL)
    res->query_raw = xmlMemStrdup(ref->query_raw);
    else if (ref->query != NULL)
    res->query = xmlMemStrdup(ref->query);
    if (ref->fragment != NULL)
    res->fragment = xmlMemStrdup(ref->fragment);
 
    /*
     * 4) If the authority component is defined, then the reference is a
     *    network-path and we skip to step 7.  Otherwise, the reference
     *    URI's authority is inherited from the base URI's authority
     *    component, which will also be undefined if the URI scheme does not
     *    use an authority component.
     */
    if ((ref->authority != NULL) || (ref->server != NULL) ||
         (ref->port != PORT_EMPTY)) {
    if (ref->authority != NULL)
        res->authority = xmlMemStrdup(ref->authority);
    else {
            if (ref->server != NULL)
                res->server = xmlMemStrdup(ref->server);
        if (ref->user != NULL)
        res->user = xmlMemStrdup(ref->user);
            res->port = ref->port;
    }
    if (ref->path != NULL)
        res->path = xmlMemStrdup(ref->path);
    goto step_7;
    }
    if (bas->authority != NULL)
    res->authority = xmlMemStrdup(bas->authority);
    else if ((bas->server != NULL) || (bas->port != PORT_EMPTY)) {
    if (bas->server != NULL)
        res->server = xmlMemStrdup(bas->server);
    if (bas->user != NULL)
        res->user = xmlMemStrdup(bas->user);
    res->port = bas->port;
    }
 
    /*
     * 5) If the path component begins with a slash character ("/"), then
     *    the reference is an absolute-path and we skip to step 7.
     */
    if ((ref->path != NULL) && (ref->path[0] == '/')) {
    res->path = xmlMemStrdup(ref->path);
    goto step_7;
    }
 
 
    /*
     * 6) If this step is reached, then we are resolving a relative-path
     *    reference.  The relative path needs to be merged with the base
     *    URI's path.  Although there are many ways to do this, we will
     *    describe a simple method using a separate string buffer.
     *
     * Allocate a buffer large enough for the result string.
     */
    len = 2; /* extra / and 0 */
    if (ref->path != NULL)
    len += strlen(ref->path);
    if (bas->path != NULL)
    len += strlen(bas->path);
    res->path = (char *) xmlMallocAtomic(len);
    if (res->path == NULL) {
        xmlURIErrMemory("resolving URI against base\n");
    goto done;
    }
    res->path[0] = 0;
 
    /*
     * a) All but the last segment of the base URI's path component is
     *    copied to the buffer.  In other words, any characters after the
     *    last (right-most) slash character, if any, are excluded.
     */
    cur = 0;
    out = 0;
    if (bas->path != NULL) {
    while (bas->path[cur] != 0) {
        while ((bas->path[cur] != 0) && (bas->path[cur] != '/'))
        cur++;
        if (bas->path[cur] == 0)
        break;
 
        cur++;
        while (out < cur) {
        res->path[out] = bas->path[out];
        out++;
        }
    }
    }
    res->path[out] = 0;
 
    /*
     * b) The reference's path component is appended to the buffer
     *    string.
     */
    if (ref->path != NULL && ref->path[0] != 0) {
    indx = 0;
    /*
     * Ensure the path includes a '/'
     */
    if ((out == 0) && ((bas->server != NULL) || bas->port != PORT_EMPTY))
        res->path[out++] = '/';
    while (ref->path[indx] != 0) {
        res->path[out++] = ref->path[indx++];
    }
    }
    res->path[out] = 0;
 
    /*
     * Steps c) to h) are really path normalization steps
     */
    xmlNormalizeURIPath(res->path);
 
step_7:
 
    /*
     * 7) The resulting URI components, including any inherited from the
     *    base URI, are recombined to give the absolute form of the URI
     *    reference.
     */
    val = xmlSaveUri(res);
 
done:
    if (ref != NULL)
    xmlFreeURI(ref);
    if (bas != NULL)
    xmlFreeURI(bas);
    if (res != NULL)
    xmlFreeURI(res);
    return(val);
}

Referenced by xmlCreateEntityParserCtxtInternal(), xmlSAX2EntityDecl(), xmlSAX2ResolveEntity(), xmlSAX2UnparsedEntityDecl(), xsltDocumentElem(), xsltDocumentFunction(), xsltLoadStylesheetPI(), xsltParseStylesheetImport(), and xsltParseStylesheetInclude().

xmlCanonicPath()

XMLPUBFUN xmlChar * xmlCanonicPath

(

const xmlChar *

path

)

Definition at line 2394 of file uri.c.

{
/*
 * For Windows implementations, additional work needs to be done to
 * replace backslashes in pathnames with "forward slashes"
 */
#if defined(_WIN32)
    int len = 0;
    char *p = NULL;
#endif
    xmlURIPtr uri;
    xmlChar *ret;
    const xmlChar *absuri;
 
    if (path == NULL)
    return(NULL);
 
#if defined(_WIN32)
    /*
     * We must not change the backslashes to slashes if the the path
     * starts with \\?\
     * Those paths can be up to 32k characters long.
     * Was added specifically for OpenOffice, those paths can't be converted
     * to URIs anyway.
     */
    if ((path[0] == '\\') && (path[1] == '\\') && (path[2] == '?') &&
        (path[3] == '\\') )
    return xmlStrdup((const xmlChar *) path);
#endif
 
    /* sanitize filename starting with // so it can be used as URI */
    if ((path[0] == '/') && (path[1] == '/') && (path[2] != '/'))
        path++;
 
    if ((uri = xmlParseURI((const char *) path)) != NULL) {
    xmlFreeURI(uri);
    return xmlStrdup(path);
    }
 
    /* Check if this is an "absolute uri" */
    absuri = xmlStrstr(path, BAD_CAST "://");
    if (absuri != NULL) {
        int l, j;
    unsigned char c;
    xmlChar *escURI;
 
        /*
     * this looks like an URI where some parts have not been
     * escaped leading to a parsing problem.  Check that the first
     * part matches a protocol.
     */
    l = absuri - path;
    /* Bypass if first part (part before the '://') is > 20 chars */
    if ((l <= 0) || (l > 20))
        goto path_processing;
    /* Bypass if any non-alpha characters are present in first part */
    for (j = 0;j < l;j++) {
        c = path[j];
        if (!(((c >= 'a') && (c <= 'z')) || ((c >= 'A') && (c <= 'Z'))))
            goto path_processing;
    }
 
    /* Escape all except the characters specified in the supplied path */
        escURI = xmlURIEscapeStr(path, BAD_CAST ":/?_.#&;=");
    if (escURI != NULL) {
        /* Try parsing the escaped path */
        uri = xmlParseURI((const char *) escURI);
        /* If successful, return the escaped string */
        if (uri != NULL) {
            xmlFreeURI(uri);
        return escURI;
        }
            xmlFree(escURI);
    }
    }
 
path_processing:
/* For Windows implementations, replace backslashes with 'forward slashes' */
#if defined(_WIN32)
    /*
     * Create a URI structure
     */
    uri = xmlCreateURI();
    if (uri == NULL) {      /* Guard against 'out of memory' */
        return(NULL);
    }
 
    len = xmlStrlen(path);
    if ((len > 2) && IS_WINDOWS_PATH(path)) {
        /* make the scheme 'file' */
    uri->scheme = (char *) xmlStrdup(BAD_CAST "file");
    /* allocate space for leading '/' + path + string terminator */
    uri->path = xmlMallocAtomic(len + 2);
    if (uri->path == NULL) {
        xmlFreeURI(uri);    /* Guard against 'out of memory' */
        return(NULL);
    }
    /* Put in leading '/' plus path */
    uri->path[0] = '/';
    p = uri->path + 1;
    strncpy(p, (char *) path, len + 1);
    } else {
    uri->path = (char *) xmlStrdup(path);
    if (uri->path == NULL) {
        xmlFreeURI(uri);
        return(NULL);
    }
    p = uri->path;
    }
    /* Now change all occurrences of '\' to '/' */
    while (*p != '\0') {
    if (*p == '\\')
        *p = '/';
    p++;
    }
 
    if (uri->scheme == NULL) {
    ret = xmlStrdup((const xmlChar *) uri->path);
    } else {
    ret = xmlSaveUri(uri);
    }
 
    xmlFreeURI(uri);
#else
    ret = xmlStrdup((const xmlChar *) path);
#endif
    return(ret);
}

Referenced by xmlCtxtResetPush(), xmlNewInputFromFile(), xmlPathToURI(), and xmlSAX2ExternalSubset().

xmlCreateURI()

XMLPUBFUN xmlURIPtr xmlCreateURI

(

void

)

xmlCreateURI:

Simply creates an empty xmlURI

Returns the new structure or NULL in case of error

Definition at line 1027 of file uri.c.

                   {
    xmlURIPtr ret;
 
    ret = (xmlURIPtr) xmlMalloc(sizeof(xmlURI));
    if (ret == NULL) {
        xmlURIErrMemory("creating URI structure\n");
    return(NULL);
    }
    memset(ret, 0, sizeof(xmlURI));
    ret->port = PORT_EMPTY;
    return(ret);
}

Referenced by xmlBuildRelativeURI(), xmlBuildURI(), xmlCanonicPath(), xmlParseURI(), xmlParseURIRaw(), xmlURIEscape(), and xsltCheckWrite().

xmlFreeURI()

XMLPUBFUN void xmlFreeURI

(

xmlURIPtr

uri

)

xmlFreeURI: @uri: pointer to an xmlURI

Free up the xmlURI struct

Definition at line 1396 of file uri.c.

                          {
    if (uri == NULL) return;
 
    if (uri->scheme != NULL) xmlFree(uri->scheme);
    if (uri->server != NULL) xmlFree(uri->server);
    if (uri->user != NULL) xmlFree(uri->user);
    if (uri->path != NULL) xmlFree(uri->path);
    if (uri->fragment != NULL) xmlFree(uri->fragment);
    if (uri->opaque != NULL) xmlFree(uri->opaque);
    if (uri->authority != NULL) xmlFree(uri->authority);
    if (uri->query != NULL) xmlFree(uri->query);
    if (uri->query_raw != NULL) xmlFree(uri->query_raw);
    xmlFree(uri);
}

Referenced by xmlBuildURI(), xmlCanonicPath(), xmlParseEntityDecl(), xmlParseStartTag2(), xmlParseURI(), xmlParseURIRaw(), xmlPathToURI(), xmlURIEscape(), xsltCheckRead(), xsltCheckWrite(), xsltDocumentFunction(), and xsltLoadStylesheetPI().

xmlNormalizeURIPath()

XMLPUBFUN int xmlNormalizeURIPath

(

char *

path

)

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

Definition at line 1429 of file uri.c.

                                {
    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;
        /* '//' normalization should be done at this point too */
        while (cur[0] == '/')
        cur++;
        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];
    }
    /* normalize // */
    while ((cur[0] == '/') && (cur[1] == '/'))
        cur++;
 
        (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, *tmp;
 
        /* 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;
        }
        /* Valgrind complained, strcpy(cur, segp + 3); */
        /* string will overlap, do not use strcpy */
        tmp = cur;
        segp += 3;
        while ((*tmp++ = *segp++) != 0)
          ;
 
        /* 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[0] == '/') && (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);
}

Referenced by xmlBuildURI().

xmlParseURI()

XMLPUBFUN xmlURIPtr xmlParseURI

(

const char *

str

)

xmlParseURI: @str: the URI string to analyze

Parse an URI based on RFC 3986

URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]

Returns a newly built xmlURIPtr or NULL in case of error

Definition at line 947 of file uri.c.

                             {
    xmlURIPtr uri;
    int ret;
 
    if (str == NULL)
    return(NULL);
    uri = xmlCreateURI();
    if (uri != NULL) {
    ret = xmlParse3986URIReference(uri, str);
        if (ret) {
        xmlFreeURI(uri);
        return(NULL);
    }
    }
    return(uri);
}

Referenced by xmlCanonicPath(), xmlParseEntityDecl(), xmlParseStartTag2(), xmlPathToURI(), xsltCheckRead(), xsltCheckWrite(), xsltDocumentFunction(), and xsltLoadStylesheetPI().

xmlParseURIRaw()

XMLPUBFUN xmlURIPtr xmlParseURIRaw	(	const char *	str,
		int	raw
	)

xmlParseURIRaw: @str: the URI string to analyze @raw: if 1 unescaping of URI pieces are disabled

Parse an URI but allows to keep intact the original fragments.

URI-reference = URI / relative-ref

Returns a newly built xmlURIPtr or NULL in case of error

Definition at line 993 of file uri.c.

                                         {
    xmlURIPtr uri;
    int ret;
 
    if (str == NULL)
    return(NULL);
    uri = xmlCreateURI();
    if (uri != NULL) {
        if (raw) {
        uri->cleanup |= 2;
    }
    ret = xmlParseURIReference(uri, str);
        if (ret) {
        xmlFreeURI(uri);
        return(NULL);
    }
    }
    return(uri);
}

xmlParseURIReference()

XMLPUBFUN int xmlParseURIReference	(	xmlURIPtr	uri,
		const char *	str
	)

xmlParseURIReference: @uri: pointer to an URI structure @str: the string to analyze

Parse an URI reference string based on RFC 3986 and fills in the appropriate fields of the @uri structure

URI-reference = URI / relative-ref

Returns 0 or the error code

Definition at line 977 of file uri.c.

                                                     {
    return(xmlParse3986URIReference(uri, str));
}

Referenced by xmlBuildRelativeURI(), xmlBuildURI(), xmlParseURIRaw(), and xmlURIEscape().

xmlPathToURI()

XMLPUBFUN xmlChar * xmlPathToURI

(

const xmlChar *

path

)

xmlPathToURI: @path: the resource locator in a filesystem notation

Constructs an URI expressing the existing path

Returns a new URI, or a duplicate of the path parameter if the construction fails. The caller is responsible for freeing the memory occupied by the returned string. If there is insufficient memory available, or the argument is NULL, the function returns NULL.

Definition at line 2535 of file uri.c.

{
    xmlURIPtr uri;
    xmlURI temp;
    xmlChar *ret, *cal;
 
    if (path == NULL)
        return(NULL);
 
    if ((uri = xmlParseURI((const char *) path)) != NULL) {
    xmlFreeURI(uri);
    return xmlStrdup(path);
    }
    cal = xmlCanonicPath(path);
    if (cal == NULL)
        return(NULL);
#if defined(_WIN32)
    /* xmlCanonicPath can return an URI on Windows (is that the intended behaviour?)
       If 'cal' is a valid URI already then we are done here, as continuing would make
       it invalid. */
    if ((uri = xmlParseURI((const char *) cal)) != NULL) {
    xmlFreeURI(uri);
    return cal;
    }
    /* 'cal' can contain a relative path with backslashes. If that is processed
       by xmlSaveURI, they will be escaped and the external entity loader machinery
       will fail. So convert them to slashes. Misuse 'ret' for walking. */
    ret = cal;
    while (*ret != '\0') {
    if (*ret == '\\')
        *ret = '/';
    ret++;
    }
#endif
    memset(&temp, 0, sizeof(temp));
    temp.path = (char *) cal;
    ret = xmlSaveUri(&temp);
    xmlFree(cal);
    return(ret);
}

Referenced by xmlSAX2StartDocument().

xmlPrintURI()

XMLPUBFUN void xmlPrintURI	(	FILE *	stream,
		xmlURIPtr	uri
	)

xmlPrintURI: @stream: a FILE* for the output @uri: pointer to an xmlURI

Prints the URI in the stream @stream.

Definition at line 1349 of file uri.c.

                                         {
    xmlChar *out;
 
    out = xmlSaveUri(uri);
    if (out != NULL) {
    fprintf(stream, "%s", (char *) out);
    xmlFree(out);
    }
}

xmlSaveUri()

XMLPUBFUN xmlChar * xmlSaveUri

(

xmlURIPtr

uri

)

xmlSaveUri: @uri: pointer to an xmlURI

Save the URI as an escaped string

Returns a new string (to be deallocated by caller)

Definition at line 1074 of file uri.c.

                          {
    xmlChar *ret = NULL;
    xmlChar *temp;
    const char *p;
    int len;
    int max;
 
    if (uri == NULL) return(NULL);
 
 
    max = 80;
    ret = (xmlChar *) xmlMallocAtomic(max + 1);
    if (ret == NULL) {
        xmlURIErrMemory("saving URI\n");
    return(NULL);
    }
    len = 0;
 
    if (uri->scheme != NULL) {
    p = uri->scheme;
    while (*p != 0) {
        if (len >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
        ret = temp;
        }
        ret[len++] = *p++;
    }
    if (len >= max) {
            temp = xmlSaveUriRealloc(ret, &max);
            if (temp == NULL) goto mem_error;
            ret = temp;
    }
    ret[len++] = ':';
    }
    if (uri->opaque != NULL) {
    p = uri->opaque;
    while (*p != 0) {
        if (len + 3 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
        }
        if (IS_RESERVED(*(p)) || IS_UNRESERVED(*(p)))
        ret[len++] = *p++;
        else {
        int val = *(unsigned char *)p++;
        int hi = val / 0x10, lo = val % 0x10;
        ret[len++] = '%';
        ret[len++] = hi + (hi > 9? 'A'-10 : '0');
        ret[len++] = lo + (lo > 9? 'A'-10 : '0');
        }
    }
    } else {
    if ((uri->server != NULL) || (uri->port != PORT_EMPTY)) {
        if (len + 3 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
        }
        ret[len++] = '/';
        ret[len++] = '/';
        if (uri->user != NULL) {
        p = uri->user;
        while (*p != 0) {
            if (len + 3 >= max) {
                        temp = xmlSaveUriRealloc(ret, &max);
                        if (temp == NULL) goto mem_error;
                        ret = temp;
            }
            if ((IS_UNRESERVED(*(p))) ||
            ((*(p) == ';')) || ((*(p) == ':')) ||
            ((*(p) == '&')) || ((*(p) == '=')) ||
            ((*(p) == '+')) || ((*(p) == '$')) ||
            ((*(p) == ',')))
            ret[len++] = *p++;
            else {
            int val = *(unsigned char *)p++;
            int hi = val / 0x10, lo = val % 0x10;
            ret[len++] = '%';
            ret[len++] = hi + (hi > 9? 'A'-10 : '0');
            ret[len++] = lo + (lo > 9? 'A'-10 : '0');
            }
        }
        if (len + 3 >= max) {
                    temp = xmlSaveUriRealloc(ret, &max);
                    if (temp == NULL) goto mem_error;
                    ret = temp;
        }
        ret[len++] = '@';
        }
        if (uri->server != NULL) {
        p = uri->server;
        while (*p != 0) {
            if (len >= max) {
            temp = xmlSaveUriRealloc(ret, &max);
            if (temp == NULL) goto mem_error;
            ret = temp;
            }
                    /* TODO: escaping? */
            ret[len++] = (xmlChar) *p++;
        }
        }
            if (uri->port > 0) {
                if (len + 10 >= max) {
                    temp = xmlSaveUriRealloc(ret, &max);
                    if (temp == NULL) goto mem_error;
                    ret = temp;
                }
                len += snprintf((char *) &ret[len], max - len, ":%d", uri->port);
            }
    } else if (uri->authority != NULL) {
        if (len + 3 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
        }
        ret[len++] = '/';
        ret[len++] = '/';
        p = uri->authority;
        while (*p != 0) {
        if (len + 3 >= max) {
                    temp = xmlSaveUriRealloc(ret, &max);
                    if (temp == NULL) goto mem_error;
                    ret = temp;
        }
        if ((IS_UNRESERVED(*(p))) ||
                    ((*(p) == '$')) || ((*(p) == ',')) || ((*(p) == ';')) ||
                    ((*(p) == ':')) || ((*(p) == '@')) || ((*(p) == '&')) ||
                    ((*(p) == '=')) || ((*(p) == '+')))
            ret[len++] = *p++;
        else {
            int val = *(unsigned char *)p++;
            int hi = val / 0x10, lo = val % 0x10;
            ret[len++] = '%';
            ret[len++] = hi + (hi > 9? 'A'-10 : '0');
            ret[len++] = lo + (lo > 9? 'A'-10 : '0');
        }
        }
    } else if (uri->scheme != NULL) {
        if (len + 3 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
        }
    }
    if (uri->path != NULL) {
        p = uri->path;
        /*
         * the colon in file:///d: should not be escaped or
         * Windows accesses fail later.
         */
        if ((uri->scheme != NULL) &&
        (p[0] == '/') &&
        (((p[1] >= 'a') && (p[1] <= 'z')) ||
         ((p[1] >= 'A') && (p[1] <= 'Z'))) &&
        (p[2] == ':') &&
            (xmlStrEqual(BAD_CAST uri->scheme, BAD_CAST "file"))) {
        if (len + 3 >= max) {
                    temp = xmlSaveUriRealloc(ret, &max);
                    if (temp == NULL) goto mem_error;
                    ret = temp;
        }
        ret[len++] = *p++;
        ret[len++] = *p++;
        ret[len++] = *p++;
        }
        while (*p != 0) {
        if (len + 3 >= max) {
                    temp = xmlSaveUriRealloc(ret, &max);
                    if (temp == NULL) goto mem_error;
                    ret = temp;
        }
        if ((IS_UNRESERVED(*(p))) || ((*(p) == '/')) ||
                    ((*(p) == ';')) || ((*(p) == '@')) || ((*(p) == '&')) ||
                ((*(p) == '=')) || ((*(p) == '+')) || ((*(p) == '$')) ||
                ((*(p) == ',')))
            ret[len++] = *p++;
        else {
            int val = *(unsigned char *)p++;
            int hi = val / 0x10, lo = val % 0x10;
            ret[len++] = '%';
            ret[len++] = hi + (hi > 9? 'A'-10 : '0');
            ret[len++] = lo + (lo > 9? 'A'-10 : '0');
        }
        }
    }
    if (uri->query_raw != NULL) {
        if (len + 1 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
        }
        ret[len++] = '?';
        p = uri->query_raw;
        while (*p != 0) {
        if (len + 1 >= max) {
                    temp = xmlSaveUriRealloc(ret, &max);
                    if (temp == NULL) goto mem_error;
                    ret = temp;
        }
        ret[len++] = *p++;
        }
    } else if (uri->query != NULL) {
        if (len + 3 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
        }
        ret[len++] = '?';
        p = uri->query;
        while (*p != 0) {
        if (len + 3 >= max) {
                    temp = xmlSaveUriRealloc(ret, &max);
                    if (temp == NULL) goto mem_error;
                    ret = temp;
        }
        if ((IS_UNRESERVED(*(p))) || (IS_RESERVED(*(p))))
            ret[len++] = *p++;
        else {
            int val = *(unsigned char *)p++;
            int hi = val / 0x10, lo = val % 0x10;
            ret[len++] = '%';
            ret[len++] = hi + (hi > 9? 'A'-10 : '0');
            ret[len++] = lo + (lo > 9? 'A'-10 : '0');
        }
        }
    }
    }
    if (uri->fragment != NULL) {
    if (len + 3 >= max) {
            temp = xmlSaveUriRealloc(ret, &max);
            if (temp == NULL) goto mem_error;
            ret = temp;
    }
    ret[len++] = '#';
    p = uri->fragment;
    while (*p != 0) {
        if (len + 3 >= max) {
                temp = xmlSaveUriRealloc(ret, &max);
                if (temp == NULL) goto mem_error;
                ret = temp;
        }
        if ((IS_UNRESERVED(*(p))) || (IS_RESERVED(*(p))))
        ret[len++] = *p++;
        else {
        int val = *(unsigned char *)p++;
        int hi = val / 0x10, lo = val % 0x10;
        ret[len++] = '%';
        ret[len++] = hi + (hi > 9? 'A'-10 : '0');
        ret[len++] = lo + (lo > 9? 'A'-10 : '0');
        }
    }
    }
    if (len >= max) {
        temp = xmlSaveUriRealloc(ret, &max);
        if (temp == NULL) goto mem_error;
        ret = temp;
    }
    ret[len] = 0;
    return(ret);
 
mem_error:
    xmlFree(ret);
    return(NULL);
}

Referenced by xmlBuildURI(), xmlCanonicPath(), xmlPathToURI(), xmlPrintURI(), and xsltDocumentFunction().

xmlURIEscape()

XMLPUBFUN xmlChar * xmlURIEscape

(

const xmlChar *

str

)

xmlURIEscape: @str: the string of the URI to escape

Escaping routine, does not do validity checks ! It will try to escape the chars needing this, but this is heuristic based it's impossible to be sure.

Returns an copy of the string, but escaped

25 May 2001 Uses xmlParseURI and xmlURIEscapeStr to try to escape correctly according to RFC2396.

• Carl Douglas

Definition at line 1762 of file uri.c.

{
    xmlChar *ret, *segment = NULL;
    xmlURIPtr uri;
    int ret2;
 
    if (str == NULL)
        return (NULL);
 
    uri = xmlCreateURI();
    if (uri != NULL) {
    /*
     * Allow escaping errors in the unescaped form
     */
        uri->cleanup = 1;
        ret2 = xmlParseURIReference(uri, (const char *)str);
        if (ret2) {
            xmlFreeURI(uri);
            return (NULL);
        }
    }
 
    if (!uri)
        return NULL;
 
    ret = NULL;
 
#define NULLCHK(p) if(!p) { \
         xmlURIErrMemory("escaping URI value\n"); \
         xmlFreeURI(uri); \
         xmlFree(ret); \
         return NULL; } \
 
    if (uri->scheme) {
        segment = xmlURIEscapeStr(BAD_CAST uri->scheme, BAD_CAST "+-.");
        NULLCHK(segment)
        ret = xmlStrcat(ret, segment);
        ret = xmlStrcat(ret, BAD_CAST ":");
        xmlFree(segment);
    }
 
    if (uri->authority) {
        segment =
            xmlURIEscapeStr(BAD_CAST uri->authority, BAD_CAST "/?;:@");
        NULLCHK(segment)
        ret = xmlStrcat(ret, BAD_CAST "//");
        ret = xmlStrcat(ret, segment);
        xmlFree(segment);
    }
 
    if (uri->user) {
        segment = xmlURIEscapeStr(BAD_CAST uri->user, BAD_CAST ";:&=+$,");
        NULLCHK(segment)
        ret = xmlStrcat(ret,BAD_CAST "//");
        ret = xmlStrcat(ret, segment);
        ret = xmlStrcat(ret, BAD_CAST "@");
        xmlFree(segment);
    }
 
    if (uri->server) {
        segment = xmlURIEscapeStr(BAD_CAST uri->server, BAD_CAST "/?;:@");
        NULLCHK(segment)
        if (uri->user == NULL)
            ret = xmlStrcat(ret, BAD_CAST "//");
        ret = xmlStrcat(ret, segment);
        xmlFree(segment);
    }
 
    if (uri->port > 0) {
        xmlChar port[11];
 
        snprintf((char *) port, 11, "%d", uri->port);
        ret = xmlStrcat(ret, BAD_CAST ":");
        ret = xmlStrcat(ret, port);
    }
 
    if (uri->path) {
        segment =
            xmlURIEscapeStr(BAD_CAST uri->path, BAD_CAST ":@&=+$,/?;");
        NULLCHK(segment)
        ret = xmlStrcat(ret, segment);
        xmlFree(segment);
    }
 
    if (uri->query_raw) {
        ret = xmlStrcat(ret, BAD_CAST "?");
        ret = xmlStrcat(ret, BAD_CAST uri->query_raw);
    }
    else if (uri->query) {
        segment =
            xmlURIEscapeStr(BAD_CAST uri->query, BAD_CAST ";/?:@&=+,$");
        NULLCHK(segment)
        ret = xmlStrcat(ret, BAD_CAST "?");
        ret = xmlStrcat(ret, segment);
        xmlFree(segment);
    }
 
    if (uri->opaque) {
        segment = xmlURIEscapeStr(BAD_CAST uri->opaque, BAD_CAST "");
        NULLCHK(segment)
        ret = xmlStrcat(ret, segment);
        xmlFree(segment);
    }
 
    if (uri->fragment) {
        segment = xmlURIEscapeStr(BAD_CAST uri->fragment, BAD_CAST "#");
        NULLCHK(segment)
        ret = xmlStrcat(ret, BAD_CAST "#");
        ret = xmlStrcat(ret, segment);
        xmlFree(segment);
    }
 
    xmlFreeURI(uri);
#undef NULLCHK
 
    return (ret);
}

xmlURIEscapeStr()

XMLPUBFUN xmlChar * xmlURIEscapeStr	(	const xmlChar *	str,
		const xmlChar *	list
	)

xmlURIEscapeStr: @str: string to escape @list: exception list string of chars not to escape

This routine escapes a string to hex, ignoring reserved characters (a-z, A-Z, 0-9, "@-_.!~*'()") and the characters in the exception list.

Returns a new escaped string or NULL in case of error.

Definition at line 1689 of file uri.c.

                                                         {
    xmlChar *ret, ch;
    xmlChar *temp;
    const xmlChar *in;
    int len, out;
 
    if (str == NULL)
    return(NULL);
    if (str[0] == 0)
    return(xmlStrdup(str));
    len = xmlStrlen(str);
    if (!(len > 0)) return(NULL);
 
    len += 20;
    ret = (xmlChar *) xmlMallocAtomic(len);
    if (ret == NULL) {
        xmlURIErrMemory("escaping URI value\n");
    return(NULL);
    }
    in = (const xmlChar *) str;
    out = 0;
    while(*in != 0) {
    if (len - out <= 3) {
            temp = xmlSaveUriRealloc(ret, &len);
        if (temp == NULL) {
                xmlURIErrMemory("escaping URI value\n");
        xmlFree(ret);
        return(NULL);
        }
        ret = temp;
    }
 
    ch = *in;
 
    if ((ch != '@') && (!IS_UNRESERVED(ch)) && (!xmlStrchr(list, ch))) {
        unsigned char val;
        ret[out++] = '%';
        val = ch >> 4;
        if (val <= 9)
        ret[out++] = '0' + val;
        else
        ret[out++] = 'A' + val - 0xA;
        val = ch & 0xF;
        if (val <= 9)
        ret[out++] = '0' + val;
        else
        ret[out++] = 'A' + val - 0xA;
        in++;
    } else {
        ret[out++] = *in++;
    }
 
    }
    ret[out] = 0;
    return(ret);
}

Referenced by xmlCanonicPath(), xmlURIEscape(), and xsltDocumentElem().

xmlURIUnescapeString()

XMLPUBFUN char * xmlURIUnescapeString	(	const char *	str,
		int	len,
		char *	target
	)

xmlURIUnescapeString: @str: the string to unescape @len: the length in bytes to unescape (or <= 0 to indicate full string) @target: optional destination buffer

Unescaping routine, but does not check that the string is an URI. The output is a direct unsigned char translation of XX values (no encoding) Note that the length of the result can only be smaller or same size as the input string.

Returns a copy of the string, but unescaped, will return NULL only in case of error

Definition at line 1629 of file uri.c.

                                                             {
    char *ret, *out;
    const char *in;
 
    if (str == NULL)
    return(NULL);
    if (len <= 0) len = strlen(str);
    if (len < 0) return(NULL);
 
    if (target == NULL) {
    ret = (char *) xmlMallocAtomic(len + 1);
    if (ret == NULL) {
            xmlURIErrMemory("unescaping URI value\n");
        return(NULL);
    }
    } else
    ret = target;
    in = str;
    out = ret;
    while(len > 0) {
    if ((len > 2) && (*in == '%') && (is_hex(in[1])) && (is_hex(in[2]))) {
            int c = 0;
        in++;
        if ((*in >= '0') && (*in <= '9'))
            c = (*in - '0');
        else if ((*in >= 'a') && (*in <= 'f'))
            c = (*in - 'a') + 10;
        else if ((*in >= 'A') && (*in <= 'F'))
            c = (*in - 'A') + 10;
        in++;
        if ((*in >= '0') && (*in <= '9'))
            c = c * 16 + (*in - '0');
        else if ((*in >= 'a') && (*in <= 'f'))
            c = c * 16 + (*in - 'a') + 10;
        else if ((*in >= 'A') && (*in <= 'F'))
            c = c * 16 + (*in - 'A') + 10;
        in++;
        len -= 3;
            /* Explicit sign change */
        *out++ = (char) c;
    } else {
        *out++ = *in++;
        len--;
    }
    }
    *out = 0;
    return(ret);
}

Referenced by xmlParse3986Fragment(), xmlParse3986Host(), xmlParse3986PathAbEmpty(), xmlParse3986PathAbsolute(), xmlParse3986PathNoScheme(), xmlParse3986PathRootless(), xmlParse3986Query(), and xmlParse3986Userinfo().