Roll libxml to 2.9.3

third_party/libxml/src/HTMLparser.c

 /*
  * HTMLparser.c : an HTML 4.0 non-verifying parser
  *
  * See Copyright for the status of this software.
  *
  * daniel@veillard.com
  */
 
 #define IN_LIBXML
 #include "libxml.h"
@@ skipping 2930 matching lines @@
              */
             ctxt->sax->cdataBlock(ctxt->userData, buf, nbchar);
         } else if (ctxt->sax->characters != NULL) {
             ctxt->sax->characters(ctxt->userData, buf, nbchar);
         }
     }
 }
 
 
 /**
- * htmlParseCharData:
+ * htmlParseCharDataInternal:
  * @ctxt:  an HTML parser context
+ * @readahead: optional read ahead character in ascii range
  *
  * parse a CharData section.
  * if we are within a CDATA section ']]>' marks an end of section.
  *
  * [14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*)
  */
 
 static void
-htmlParseCharData(htmlParserCtxtPtr ctxt) {
-    xmlChar buf[HTML_PARSER_BIG_BUFFER_SIZE + 5];
+htmlParseCharDataInternal(htmlParserCtxtPtr ctxt, int readahead) {
+    xmlChar buf[HTML_PARSER_BIG_BUFFER_SIZE + 6];
     int nbchar = 0;
     int cur, l;
     int chunk = 0;
 
+    if (readahead)
+        buf[nbchar++] = readahead;
+
     SHRINK;
     cur = CUR_CHAR(l);
     while (((cur != '<') || (ctxt->token == '<')) &&
            ((cur != '&') || (ctxt->token == '&')) &&
            (cur != 0)) {
         if (!(IS_CHAR(cur))) {
             htmlParseErrInt(ctxt, XML_ERR_INVALID_CHAR,
                         "Invalid char in CDATA 0x%X\n", cur);
         } else {
             COPY_BUF(l,buf,nbchar,cur);
@@ skipping 59 matching lines @@
     } else {
         /*
          * Loop detection
          */
         if (cur == 0)
             ctxt->instate = XML_PARSER_EOF;
     }
 }
 
 /**
+ * htmlParseCharData:
+ * @ctxt:  an HTML parser context
+ *
+ * parse a CharData section.
+ * if we are within a CDATA section ']]>' marks an end of section.
+ *
+ * [14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*)
+ */
+
+static void
+htmlParseCharData(htmlParserCtxtPtr ctxt) {
+    htmlParseCharDataInternal(ctxt, 0);
+}
+
+/**
  * htmlParseExternalID:
  * @ctxt:  an HTML parser context
  * @publicID:  a xmlChar** receiving PubidLiteral
  *
  * Parse an External ID or a Public ID
  *
  * [75] ExternalID ::= 'SYSTEM' S SystemLiteral
  *                   | 'PUBLIC' S PubidLiteral S SystemLiteral
  *
  * [83] PublicID ::= 'PUBLIC' S PubidLiteral
@@ skipping 182 matching lines @@
     state = ctxt->instate;
     ctxt->instate = XML_PARSER_COMMENT;
     SHRINK;
     SKIP(4);
     buf = (xmlChar *) xmlMallocAtomic(size * sizeof(xmlChar));
     if (buf == NULL) {
         htmlErrMemory(ctxt, "buffer allocation failed\n");
         ctxt->instate = state;
         return;
     }
+    len = 0;
+    buf[len] = 0;
     q = CUR_CHAR(ql);
+    if (!IS_CHAR(q))
+        goto unfinished;
     NEXTL(ql);
     r = CUR_CHAR(rl);
+    if (!IS_CHAR(r))
+        goto unfinished;
     NEXTL(rl);
     cur = CUR_CHAR(l);
-    len = 0;
     while (IS_CHAR(cur) &&
            ((cur != '>') ||
             (r != '-') || (q != '-'))) {
         if (len + 5 >= size) {
             xmlChar *tmp;
 
             size *= 2;
             tmp = (xmlChar *) xmlRealloc(buf, size * sizeof(xmlChar));
             if (tmp == NULL) {
                 xmlFree(buf);
@@ skipping 10 matching lines @@
         rl = l;
         NEXTL(l);
         cur = CUR_CHAR(l);
         if (cur == 0) {
             SHRINK;
             GROW;
             cur = CUR_CHAR(l);
         }
     }
     buf[len] = 0;
-    if (!IS_CHAR(cur)) {
-        htmlParseErr(ctxt, XML_ERR_COMMENT_NOT_FINISHED,
-                     "Comment not terminated \n<!--%.50s\n", buf, NULL);
-        xmlFree(buf);
-    } else {
+    if (IS_CHAR(cur)) {
         NEXT;
         if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) &&
             (!ctxt->disableSAX))
             ctxt->sax->comment(ctxt->userData, buf);
         xmlFree(buf);
+        ctxt->instate = state;
+        return;
     }
-    ctxt->instate = state;
+
+unfinished:
+    htmlParseErr(ctxt, XML_ERR_COMMENT_NOT_FINISHED,
+                 "Comment not terminated \n<!--%.50s\n", buf, NULL);
+    xmlFree(buf);
 }
 
 /**
  * htmlParseCharRef:
  * @ctxt:  an HTML parser context
  *
  * parse Reference declarations
  *
  * [66] CharRef ::= '&#' [0-9]+ ';' |
  *                  '&#x' [0-9a-fA-F]+ ';'
@@ skipping 377 matching lines @@
 
     atts = ctxt->atts;
     maxatts = ctxt->maxatts;
 
     GROW;
     name = htmlParseHTMLName(ctxt);
     if (name == NULL) {
         htmlParseErr(ctxt, XML_ERR_NAME_REQUIRED,
                      "htmlParseStartTag: invalid element name\n",
                      NULL, NULL);
+        /* if recover preserve text on classic misconstructs */
+        if ((ctxt->recovery) && ((IS_BLANK_CH(CUR)) || (CUR == '<') ||
+            (CUR == '=') || (CUR == '>') || (((CUR >= '0') && (CUR <= '9'))))) {
+            htmlParseCharDataInternal(ctxt, '<');
+            return(-1);
+        }
+
+
         /* Dump the bogus tag like browsers do */
         while ((IS_CHAR_CH(CUR)) && (CUR != '>') &&
                (ctxt->instate != XML_PARSER_EOF))
             NEXT;
         return -1;
     }
     if (xmlStrEqual(name, BAD_CAST"meta"))
         meta = 1;
 
     /*
@@ skipping 1991 matching lines @@
                     ctxt->checkIndex = 0;
                 }
                 if ((avail == 1) && (terminate)) {
                     cur = in->cur[0];
                     if ((cur != '<') && (cur != '&')) {
                         if (ctxt->sax != NULL) {
                             if (IS_BLANK_CH(cur)) {
                                 if (ctxt->keepBlanks) {
                                     if (ctxt->sax->characters != NULL)
                                         ctxt->sax->characters(
-                                                ctxt->userData, &cur, 1);
+                                                ctxt->userData, &in->cur[0], 1);
                                 } else {
                                     if (ctxt->sax->ignorableWhitespace != NULL)
                                         ctxt->sax->ignorableWhitespace(
-                                                ctxt->userData, &cur, 1);
+                                                ctxt->userData, &in->cur[0], 1);
                                 }
                             } else {
                                 htmlCheckParagraph(ctxt);
                                 if (ctxt->sax->characters != NULL)
                                     ctxt->sax->characters(
-                                            ctxt->userData, &cur, 1);
+                                            ctxt->userData, &in->cur[0], 1);
                             }
                         }
                         ctxt->token = 0;
                         ctxt->checkIndex = 0;
                         in->cur++;
                         break;
                     }
                 }
                 if (avail < 2)
                     goto done;
@@ skipping 1353 matching lines @@
         xmlFreeParserInputBuffer(input);
         return (NULL);
     }
     inputPush(ctxt, stream);
     return (htmlDoRead(ctxt, URL, encoding, options, 1));
 }
 
 #define bottom_HTMLparser
 #include "elfgcchack.h"
 #endif /* LIBXML_HTML_ENABLED */