summaryrefslogtreecommitdiff
path: root/parser.c
diff options
context:
space:
mode:
Diffstat (limited to 'parser.c')
-rw-r--r--parser.c208
1 files changed, 168 insertions, 40 deletions
diff --git a/parser.c b/parser.c
index 85e7599..d1c7888 100644
--- a/parser.c
+++ b/parser.c
@@ -954,6 +954,12 @@ xmlHasFeature(xmlFeature feature)
#else
return(0);
#endif
+ case XML_WITH_ICU:
+#ifdef LIBXML_ICU_ENABLED
+ return(1);
+#else
+ return(0);
+#endif
default:
break;
}
@@ -1297,60 +1303,182 @@ xmlCleanSpecialAttr(xmlParserCtxtPtr ctxt)
* [37] UserCode ::= ('x' | 'X') '-' ([a-z] | [A-Z])+
* [38] Subcode ::= ([a-z] | [A-Z])+
*
+ * The current REC reference the sucessors of RFC 1766, currently 5646
+ *
+ * http://www.rfc-editor.org/rfc/rfc5646.txt
+ * langtag = language
+ * ["-" script]
+ * ["-" region]
+ * *("-" variant)
+ * *("-" extension)
+ * ["-" privateuse]
+ * language = 2*3ALPHA ; shortest ISO 639 code
+ * ["-" extlang] ; sometimes followed by
+ * ; extended language subtags
+ * / 4ALPHA ; or reserved for future use
+ * / 5*8ALPHA ; or registered language subtag
+ *
+ * extlang = 3ALPHA ; selected ISO 639 codes
+ * *2("-" 3ALPHA) ; permanently reserved
+ *
+ * script = 4ALPHA ; ISO 15924 code
+ *
+ * region = 2ALPHA ; ISO 3166-1 code
+ * / 3DIGIT ; UN M.49 code
+ *
+ * variant = 5*8alphanum ; registered variants
+ * / (DIGIT 3alphanum)
+ *
+ * extension = singleton 1*("-" (2*8alphanum))
+ *
+ * ; Single alphanumerics
+ * ; "x" reserved for private use
+ * singleton = DIGIT ; 0 - 9
+ * / %x41-57 ; A - W
+ * / %x59-5A ; Y - Z
+ * / %x61-77 ; a - w
+ * / %x79-7A ; y - z
+ *
+ * it sounds right to still allow Irregular i-xxx IANA and user codes too
+ * The parser below doesn't try to cope with extension or privateuse
+ * that could be added but that's not interoperable anyway
+ *
* Returns 1 if correct 0 otherwise
**/
int
xmlCheckLanguageID(const xmlChar * lang)
{
- const xmlChar *cur = lang;
+ const xmlChar *cur = lang, *nxt;
if (cur == NULL)
return (0);
if (((cur[0] == 'i') && (cur[1] == '-')) ||
- ((cur[0] == 'I') && (cur[1] == '-'))) {
- /*
- * IANA code
- */
- cur += 2;
- while (((cur[0] >= 'A') && (cur[0] <= 'Z')) || /* non input consuming */
- ((cur[0] >= 'a') && (cur[0] <= 'z')))
- cur++;
- } else if (((cur[0] == 'x') && (cur[1] == '-')) ||
- ((cur[0] == 'X') && (cur[1] == '-'))) {
+ ((cur[0] == 'I') && (cur[1] == '-')) ||
+ ((cur[0] == 'x') && (cur[1] == '-')) ||
+ ((cur[0] == 'X') && (cur[1] == '-'))) {
/*
- * User code
+ * Still allow IANA code and user code which were coming
+ * from the previous version of the XML-1.0 specification
+ * it's deprecated but we should not fail
*/
cur += 2;
- while (((cur[0] >= 'A') && (cur[0] <= 'Z')) || /* non input consuming */
+ while (((cur[0] >= 'A') && (cur[0] <= 'Z')) ||
((cur[0] >= 'a') && (cur[0] <= 'z')))
cur++;
- } else if (((cur[0] >= 'A') && (cur[0] <= 'Z')) ||
- ((cur[0] >= 'a') && (cur[0] <= 'z'))) {
+ return(cur[0] == 0);
+ }
+ nxt = cur;
+ while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) ||
+ ((nxt[0] >= 'a') && (nxt[0] <= 'z')))
+ nxt++;
+ if (nxt - cur >= 4) {
/*
- * ISO639
+ * Reserved
*/
- cur++;
- if (((cur[0] >= 'A') && (cur[0] <= 'Z')) ||
- ((cur[0] >= 'a') && (cur[0] <= 'z')))
- cur++;
- else
- return (0);
- } else
- return (0);
- while (cur[0] != 0) { /* non input consuming */
- if (cur[0] != '-')
- return (0);
- cur++;
- if (((cur[0] >= 'A') && (cur[0] <= 'Z')) ||
- ((cur[0] >= 'a') && (cur[0] <= 'z')))
- cur++;
- else
- return (0);
- while (((cur[0] >= 'A') && (cur[0] <= 'Z')) || /* non input consuming */
- ((cur[0] >= 'a') && (cur[0] <= 'z')))
- cur++;
+ if ((nxt - cur > 8) || (nxt[0] != 0))
+ return(0);
+ return(1);
}
+ if (nxt - cur < 2)
+ return(0);
+ /* we got an ISO 639 code */
+ if (nxt[0] == 0)
+ return(1);
+ if (nxt[0] != '-')
+ return(0);
+
+ nxt++;
+ cur = nxt;
+ /* now we can have extlang or script or region or variant */
+ if ((nxt[0] >= '0') && (nxt[0] <= '9'))
+ goto region_m49;
+
+ while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) ||
+ ((nxt[0] >= 'a') && (nxt[0] <= 'z')))
+ nxt++;
+ if (nxt - cur == 4)
+ goto script;
+ if (nxt - cur == 2)
+ goto region;
+ if ((nxt - cur >= 5) && (nxt - cur <= 8))
+ goto variant;
+ if (nxt - cur != 3)
+ return(0);
+ /* we parsed an extlang */
+ if (nxt[0] == 0)
+ return(1);
+ if (nxt[0] != '-')
+ return(0);
+
+ nxt++;
+ cur = nxt;
+ /* now we can have script or region or variant */
+ if ((nxt[0] >= '0') && (nxt[0] <= '9'))
+ goto region_m49;
+
+ while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) ||
+ ((nxt[0] >= 'a') && (nxt[0] <= 'z')))
+ nxt++;
+ if (nxt - cur == 2)
+ goto region;
+ if ((nxt - cur >= 5) && (nxt - cur <= 8))
+ goto variant;
+ if (nxt - cur != 4)
+ return(0);
+ /* we parsed a script */
+script:
+ if (nxt[0] == 0)
+ return(1);
+ if (nxt[0] != '-')
+ return(0);
+
+ nxt++;
+ cur = nxt;
+ /* now we can have region or variant */
+ if ((nxt[0] >= '0') && (nxt[0] <= '9'))
+ goto region_m49;
+
+ while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) ||
+ ((nxt[0] >= 'a') && (nxt[0] <= 'z')))
+ nxt++;
+
+ if ((nxt - cur >= 5) && (nxt - cur <= 8))
+ goto variant;
+ if (nxt - cur != 2)
+ return(0);
+ /* we parsed a region */
+region:
+ if (nxt[0] == 0)
+ return(1);
+ if (nxt[0] != '-')
+ return(0);
+
+ nxt++;
+ cur = nxt;
+ /* now we can just have a variant */
+ while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) ||
+ ((nxt[0] >= 'a') && (nxt[0] <= 'z')))
+ nxt++;
+
+ if ((nxt - cur < 5) || (nxt - cur > 8))
+ return(0);
+
+ /* we parsed a variant */
+variant:
+ if (nxt[0] == 0)
+ return(1);
+ if (nxt[0] != '-')
+ return(0);
+ /* extensions and private use subtags not checked */
return (1);
+
+region_m49:
+ if (((nxt[1] >= '0') && (nxt[1] <= '9')) &&
+ ((nxt[2] >= '0') && (nxt[2] <= '9'))) {
+ nxt += 3;
+ goto region;
+ }
+ return(0);
}
/************************************************************************
@@ -6609,7 +6737,7 @@ xmlParseExternalSubset(xmlParserCtxtPtr ctxt, const xmlChar *ExternalID,
xmlDetectSAX2(ctxt);
GROW;
- if ((ctxt->encoding == (const xmlChar *)XML_CHAR_ENCODING_NONE) &&
+ if ((ctxt->encoding == NULL) &&
(ctxt->input->end - ctxt->input->cur >= 4)) {
xmlChar start[4];
xmlCharEncoding enc;
@@ -10105,7 +10233,7 @@ xmlParseDocument(xmlParserCtxtPtr ctxt) {
if ((ctxt->sax) && (ctxt->sax->setDocumentLocator))
ctxt->sax->setDocumentLocator(ctxt->userData, &xmlDefaultSAXLocator);
- if ((ctxt->encoding == (const xmlChar *)XML_CHAR_ENCODING_NONE) &&
+ if ((ctxt->encoding == NULL) &&
((ctxt->input->end - ctxt->input->cur) >= 4)) {
/*
* Get the 4 first bytes and decode the charset
@@ -11567,7 +11695,7 @@ xmldecl_done:
* if size is greater than len. Otherwise, memmove in xmlBufferAdd
* will blindly copy extra bytes from memory.
*/
- if (size > len) {
+ if ((unsigned int) size > len) {
remain = size - len;
size = len;
} else {
@@ -14004,8 +14132,8 @@ xmlInitParser(void) {
__xmlGlobalInitMutexLock();
if (xmlParserInitialized == 0) {
#endif
- xmlInitGlobals();
xmlInitThreads();
+ xmlInitGlobals();
if ((xmlGenericError == xmlGenericErrorDefaultFunc) ||
(xmlGenericError == NULL))
initGenericErrorDefaultFunc(NULL);
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-18 18:03:21 +0000