uri.c

xml开源解析代码.版本为libxml2-2.6.29,可支持GB3212.网络消息发送XML时很有用.

	    }
	}
    }
    if (uri->fragment != NULL) {
	if (len + 3 >= max) {
	    max *= 2;
	    ret = (xmlChar *) xmlRealloc(ret,
		    (max + 1) * sizeof(xmlChar));
	    if (ret == NULL) {
		xmlGenericError(xmlGenericErrorContext,
			"xmlSaveUri: out of memory\n");
		return(NULL);
	    }
	}
	ret[len++] = '#';
	p = uri->fragment;
	while (*p != 0) {
	    if (len + 3 >= max) {
		max *= 2;
		ret = (xmlChar *) xmlRealloc(ret,
			(max + 1) * sizeof(xmlChar));
		if (ret == NULL) {
		    xmlGenericError(xmlGenericErrorContext,
			    "xmlSaveUri: out of memory\n");
		    return(NULL);
		}
	    }
	    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) {
	max *= 2;
	ret = (xmlChar *) xmlRealloc(ret, (max + 1) * sizeof(xmlChar));
	if (ret == NULL) {
	    xmlGenericError(xmlGenericErrorContext,
		    "xmlSaveUri: out of memory\n");
	    return(NULL);
	}
    }
    ret[len++] = 0;
    return(ret);
}

/**
 * xmlPrintURI:
 * @stream:  a FILE* for the output
 * @uri:  pointer to an xmlURI
 *
 * Prints the URI in the stream @stream.
 */
void
xmlPrintURI(FILE *stream, xmlURIPtr uri) {
    xmlChar *out;

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

/**
 * xmlCleanURI:
 * @uri:  pointer to an xmlURI
 *
 * Make sure the xmlURI struct is free of content
 */
static void
xmlCleanURI(xmlURIPtr uri) {
    if (uri == NULL) return;

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

/**
 * xmlFreeURI:
 * @uri:  pointer to an xmlURI
 *
 * Free up the xmlURI struct
 */
void
xmlFreeURI(xmlURIPtr uri) {
    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);
}

/************************************************************************
 *									*
 *			Helper functions				*
 *									*
 ************************************************************************/

/**
 * 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;
	    /* '//' 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];
	}
	/* nomalize // */
	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);
}

static int is_hex(char c) {
    if (((c >= '0') && (c <= '9')) ||
        ((c >= 'a') && (c <= 'f')) ||
        ((c >= 'A') && (c <= 'F')))
	return(1);
    return(0);
}

/**
 * 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
 */
char *
xmlURIUnescapeString(const char *str, int len, char *target) {
    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) {
	    xmlGenericError(xmlGenericErrorContext,
		    "xmlURIUnescapeString: out of memory\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]))) {
	    in++;
	    if ((*in >= '0') && (*in <= '9')) 
	        *out = (*in - '0');
	    else if ((*in >= 'a') && (*in <= 'f'))
	        *out = (*in - 'a') + 10;
	    else if ((*in >= 'A') && (*in <= 'F'))
	        *out = (*in - 'A') + 10;
	    in++;
	    if ((*in >= '0') && (*in <= '9')) 
	        *out = *out * 16 + (*in - '0');
	    else if ((*in >= 'a') && (*in <= 'f'))
	        *out = *out * 16 + (*in - 'a') + 10;
	    else if ((*in >= 'A') && (*in <= 'F'))
	        *out = *out * 16 + (*in - 'A') + 10;
	    in++;
	    len -= 3;
	    out++;
	} else {
	    *out++ = *in++;
	    len--;
	}
    }
    *out = 0;
    return(ret);
}

/**
 * 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)
 * and the characters in the exception list.
 *
 * Returns a new escaped string or NULL in case of error.
 */
xmlChar *
xmlURIEscapeStr(const xmlChar *str, const xmlChar *list) {
    xmlChar *ret, ch;
    const xmlChar *in;

    unsigned 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) {
	xmlGenericError(xmlGenericErrorContext,
		"xmlURIEscapeStr: out of memory\n");
	return(NULL);
    }
    in = (const xmlChar *) str;
    out = 0;
    while(*in != 0) {
	if (len - out <= 3) {
	    len += 20;
	    ret = (xmlChar *) xmlRealloc(ret, len);
	    if (ret == NULL) {
		xmlGenericError(xmlGenericErrorContext,
			"xmlURIEscapeStr: out of memory\n");
		return(NULL);
	    }
	}

	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);
}

/**
 * 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
 */
xmlChar *
xmlURIEscape(const xmlChar * str)
{
    xmlChar *ret, *segment = NULL;
    xmlURIPtr uri;
    int ret2;

#define NULLCHK(p) if(!p) { \
                   xmlGenericError(xmlGenericErrorContext, \
                        "xmlURIEscape: out of memory\n"); \
                   return NULL; }

    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;

    if (uri->scheme) {
        segment = xmlURIEscapeStr(BAD_CAST uri->scheme, BAD_CAST "+-.");
        NULLCHK(segment)
        ret = xmlStrcat(ret, segment);