static xmlCharEncoding sniff_encoding(saxctxt* ctx, const char* cbuf, size_t bytes)
{
request_rec* r = ctx->f->r;
cdn_conf* cfg = ctx->cfg;
xmlCharEncoding ret;
char* p;
ap_regmatch_t match[2];
char* buf = (char*)cbuf;
const char *encoding = 0;
/* If we've got it in the HTTP headers, there's nothing to do */
if(r->content_type && (p = ap_strcasestr(r->content_type, "charset=")) && p != NULL) {
p += 8;
if((encoding = apr_pstrndup(r->pool, p, strcspn(p, " ;")))) {
ap_log_error(APLOG_MARK, APLOG_DEBUG, APR_SUCCESS, r->server,
"sniff_encoding: found charset %s in Content-Type", encoding);
ret = xmlParseCharEncoding(encoding);
if(((ret != XML_CHAR_ENCODING_ERROR) && (ret != XML_CHAR_ENCODING_NONE)))
return ret;
}
}
/* to sniff, first we look for BOM */
if(encoding == NULL) {
if((ret = xmlDetectCharEncoding((const xmlChar*)buf, bytes)) != XML_CHAR_ENCODING_NONE) {
ap_log_error(APLOG_MARK, APLOG_DEBUG, APR_SUCCESS, r->server,
"sniff_encoding: got charset from XML rules");
return ret;
}
/* If none of the above, look for a META-thingey */
if(ap_regexec(seek_meta_ctype, buf, 1, match, 0) == 0) {
p = apr_pstrndup(r->pool, buf + match[0].rm_so, match[0].rm_eo - match[0].rm_so);
if(ap_regexec(seek_charset, p, 2, match, 0) == 0)
encoding = apr_pstrndup(r->pool, p+match[1].rm_so, match[1].rm_eo - match[1].rm_so);
}
}
/* either it's set to something we found or it's still the default */
if(encoding) {
ap_log_error(APLOG_MARK, APLOG_DEBUG, APR_SUCCESS, r->server,
"sniff_encoding: got charset %s from HTML META", encoding);
ret = xmlParseCharEncoding(encoding);
if(ret != XML_CHAR_ENCODING_ERROR && ret != XML_CHAR_ENCODING_NONE)
return ret;
ap_log_error(APLOG_MARK, APLOG_DEBUG, APR_SUCCESS, r->server,
"sniff_encoding: charset %s not supported", encoding);
}
/* Use configuration default as a last resort */
ap_log_error(APLOG_MARK, APLOG_DEBUG, APR_SUCCESS, r->server,
"sniff_encoding: no suitable charset information");
return (cfg->default_encoding == XML_CHAR_ENCODING_NONE)
? XML_CHAR_ENCODING_8859_1 : cfg->default_encoding ;
}
static apr_status_t filter_harness(ap_filter_t *f, apr_bucket_brigade *bb)
{
apr_status_t ret;
#ifndef NO_PROTOCOL
const char *cachecontrol;
#endif
harness_ctx *ctx = f->ctx;
ap_filter_rec_t *filter = f->frec;
if (f->r->status != 200
&& !apr_table_get(f->r->subprocess_env, "filter-errordocs")) {
ap_remove_output_filter(f);
return ap_pass_brigade(f->next, bb);
}
filter_trace(f->c, filter->debug, f->frec->name, bb);
/* look up a handler function if we haven't already set it */
if (!ctx->func) {
#ifndef NO_PROTOCOL
if (f->r->proxyreq) {
if (filter->proto_flags & AP_FILTER_PROTO_NO_PROXY) {
ap_remove_output_filter(f);
return ap_pass_brigade(f->next, bb);
}
if (filter->proto_flags & AP_FILTER_PROTO_TRANSFORM) {
cachecontrol = apr_table_get(f->r->headers_out,
"Cache-Control");
if (cachecontrol) {
if (ap_strcasestr(cachecontrol, "no-transform")) {
ap_remove_output_filter(f);
return ap_pass_brigade(f->next, bb);
}
}
}
}
#endif
if (!filter_lookup(f, filter)) {
ap_remove_output_filter(f);
return ap_pass_brigade(f->next, bb);
}
AP_DEBUG_ASSERT(ctx->func != NULL);
}
/* call the content filter with its own context, then restore our
* context
*/
f->ctx = ctx->fctx;
ret = ctx->func(f, bb);
ctx->fctx = f->ctx;
f->ctx = ctx;
return ret;
}
static int filter_lookup(ap_filter_t *f, ap_filter_rec_t *filter)
{
ap_filter_provider_t *provider;
int match = 0;
const char *err = NULL;
request_rec *r = f->r;
harness_ctx *ctx = f->ctx;
provider_ctx *pctx;
#ifndef NO_PROTOCOL
unsigned int proto_flags;
mod_filter_ctx *rctx = ap_get_module_config(r->request_config,
&filter_module);
#endif
/* Check registered providers in order */
for (provider = filter->providers; provider; provider = provider->next) {
if (provider->expr) {
match = ap_expr_exec(r, provider->expr, &err);
if (err) {
ap_log_rerror(APLOG_MARK, APLOG_ERR, 0, r, APLOGNO(01379)
"Error evaluating filter dispatch condition: %s",
err);
match = 0;
}
ap_log_rerror(APLOG_MARK, APLOG_TRACE2, 0, r,
"Expression condition for '%s' %s",
provider->frec->name,
match ? "matched" : "did not match");
}
else if (r->content_type) {
const char **type = provider->types;
size_t len = strcspn(r->content_type, "; \t");
AP_DEBUG_ASSERT(type != NULL);
ap_log_rerror(APLOG_MARK, APLOG_TRACE4, 0, r,
"Content-Type '%s' ...", r->content_type);
while (*type) {
/* Handle 'content-type;charset=...' correctly */
if (strncmp(*type, r->content_type, len) == 0
&& (*type)[len] == '\0') {
ap_log_rerror(APLOG_MARK, APLOG_TRACE4, 0, r,
"... matched '%s'", *type);
match = 1;
break;
}
else {
ap_log_rerror(APLOG_MARK, APLOG_TRACE4, 0, r,
"... did not match '%s'", *type);
}
type++;
}
ap_log_rerror(APLOG_MARK, APLOG_TRACE2, 0, r,
"Content-Type condition for '%s' %s",
provider->frec->name,
match ? "matched" : "did not match");
}
else {
ap_log_rerror(APLOG_MARK, APLOG_TRACE2, 0, r,
"Content-Type condition for '%s' did not match: "
"no Content-Type", provider->frec->name);
}
if (match) {
/* condition matches this provider */
#ifndef NO_PROTOCOL
/* check protocol
*
* FIXME:
* This is a quick hack and almost certainly buggy.
* The idea is that by putting this in mod_filter, we relieve
* filter implementations of the burden of fixing up HTTP headers
* for cases that are routinely affected by filters.
*
* Default is ALWAYS to do nothing, so as not to tread on the
* toes of filters which want to do it themselves.
*
*/
proto_flags = provider->frec->proto_flags;
/* some specific things can't happen in a proxy */
if (r->proxyreq) {
if (proto_flags & AP_FILTER_PROTO_NO_PROXY) {
/* can't use this provider; try next */
continue;
}
if (proto_flags & AP_FILTER_PROTO_TRANSFORM) {
const char *str = apr_table_get(r->headers_out,
"Cache-Control");
if (str) {
if (ap_strcasestr(str, "no-transform")) {
/* can't use this provider; try next */
continue;
}
}
apr_table_addn(r->headers_out, "Warning",
apr_psprintf(r->pool,
"214 %s Transformation applied",
r->hostname));
}
}
/* things that are invalidated if the filter transforms content */
if (proto_flags & AP_FILTER_PROTO_CHANGE) {
apr_table_unset(r->headers_out, "Content-MD5");
apr_table_unset(r->headers_out, "ETag");
if (proto_flags & AP_FILTER_PROTO_CHANGE_LENGTH) {
apr_table_unset(r->headers_out, "Content-Length");
}
}
/* no-cache is for a filter that has different effect per-hit */
if (proto_flags & AP_FILTER_PROTO_NO_CACHE) {
apr_table_unset(r->headers_out, "Last-Modified");
apr_table_addn(r->headers_out, "Cache-Control", "no-cache");
}
if (proto_flags & AP_FILTER_PROTO_NO_BYTERANGE) {
apr_table_setn(r->headers_out, "Accept-Ranges", "none");
}
else if (rctx && rctx->range) {
/* restore range header we saved earlier */
apr_table_setn(r->headers_in, "Range", rctx->range);
rctx->range = NULL;
}
#endif
for (pctx = ctx->init_ctx; pctx; pctx = pctx->next) {
if (pctx->provider == provider) {
ctx->fctx = pctx->ctx ;
}
}
ctx->func = provider->frec->filter_func.out_func;
return 1;
}
}
/* No provider matched */
return 0;
}
