patch from johan@evenhuis.nl for #107937 fixing some line counting
* HTMLparser.c parser.c parserInternals.c: patch from
johan@evenhuis.nl for #107937 fixing some line counting
problems, and some other cleanups.
* result/HTML/: this result in some line number changes
Daniel
diff --git a/parserInternals.c b/parserInternals.c
index 6555144..3900a0e 100644
--- a/parserInternals.c
+++ b/parserInternals.c
@@ -1095,120 +1095,131 @@
*/
void
-xmlNextChar(xmlParserCtxtPtr ctxt) {
+xmlNextChar(xmlParserCtxtPtr ctxt)
+{
if (ctxt->instate == XML_PARSER_EOF)
- return;
+ return;
- /*
- * 2.11 End-of-Line Handling
- * the literal two-character sequence "#xD#xA" or a standalone
- * literal #xD, an XML processor must pass to the application
- * the single character #xA.
- */
if (ctxt->charset == XML_CHAR_ENCODING_UTF8) {
- if ((*ctxt->input->cur == 0) &&
- (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0) &&
- (ctxt->instate != XML_PARSER_COMMENT)) {
- /*
- * If we are at the end of the current entity and
- * the context allows it, we pop consumed entities
- * automatically.
- * the auto closing should be blocked in other cases
- */
- xmlPopInput(ctxt);
- } else {
- if (*(ctxt->input->cur) == '\n') {
- ctxt->input->line++; ctxt->input->col = 1;
- } else ctxt->input->col++;
- if (ctxt->charset == XML_CHAR_ENCODING_UTF8) {
- /*
- * We are supposed to handle UTF8, check it's valid
- * From rfc2044: encoding of the Unicode values on UTF-8:
- *
- * UCS-4 range (hex.) UTF-8 octet sequence (binary)
- * 0000 0000-0000 007F 0xxxxxxx
- * 0000 0080-0000 07FF 110xxxxx 10xxxxxx
- * 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx
- *
- * Check for the 0x110000 limit too
- */
- const unsigned char *cur = ctxt->input->cur;
- unsigned char c;
+ if ((*ctxt->input->cur == 0) &&
+ (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0) &&
+ (ctxt->instate != XML_PARSER_COMMENT)) {
+ /*
+ * If we are at the end of the current entity and
+ * the context allows it, we pop consumed entities
+ * automatically.
+ * the auto closing should be blocked in other cases
+ */
+ xmlPopInput(ctxt);
+ } else {
+ const unsigned char *cur;
+ unsigned char c;
- c = *cur;
- if (c & 0x80) {
- if (cur[1] == 0)
- xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
- if ((cur[1] & 0xc0) != 0x80)
- goto encoding_error;
- if ((c & 0xe0) == 0xe0) {
- unsigned int val;
+ /*
+ * 2.11 End-of-Line Handling
+ * the literal two-character sequence "#xD#xA" or a standalone
+ * literal #xD, an XML processor must pass to the application
+ * the single character #xA.
+ */
+ if (*(ctxt->input->cur) == '\n') {
+ ctxt->input->line++;
+ ctxt->input->col = 1;
+ } else
+ ctxt->input->col++;
- if (cur[2] == 0)
- xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
- if ((cur[2] & 0xc0) != 0x80)
- goto encoding_error;
- if ((c & 0xf0) == 0xf0) {
- if (cur[3] == 0)
- xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
- if (((c & 0xf8) != 0xf0) ||
- ((cur[3] & 0xc0) != 0x80))
- goto encoding_error;
- /* 4-byte code */
- ctxt->input->cur += 4;
- val = (cur[0] & 0x7) << 18;
- val |= (cur[1] & 0x3f) << 12;
- val |= (cur[2] & 0x3f) << 6;
- val |= cur[3] & 0x3f;
- } else {
- /* 3-byte code */
- ctxt->input->cur += 3;
- val = (cur[0] & 0xf) << 12;
- val |= (cur[1] & 0x3f) << 6;
- val |= cur[2] & 0x3f;
- }
- if (((val > 0xd7ff) && (val < 0xe000)) ||
- ((val > 0xfffd) && (val < 0x10000)) ||
- (val >= 0x110000)) {
- if ((ctxt->sax != NULL) &&
- (ctxt->sax->error != NULL))
- ctxt->sax->error(ctxt->userData,
- "Char 0x%X out of allowed range\n", val);
- ctxt->errNo = XML_ERR_INVALID_ENCODING;
- ctxt->wellFormed = 0;
- if (ctxt->recovery == 0) ctxt->disableSAX = 1;
- }
- } else
- /* 2-byte code */
- ctxt->input->cur += 2;
- } else
- /* 1-byte code */
- ctxt->input->cur++;
- } else {
- /*
- * Assume it's a fixed length encoding (1) with
- * a compatible encoding for the ASCII set, since
- * XML constructs only use < 128 chars
- */
- ctxt->input->cur++;
- }
- ctxt->nbChars++;
- if (*ctxt->input->cur == 0)
- xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
- }
+ /*
+ * We are supposed to handle UTF8, check it's valid
+ * From rfc2044: encoding of the Unicode values on UTF-8:
+ *
+ * UCS-4 range (hex.) UTF-8 octet sequence (binary)
+ * 0000 0000-0000 007F 0xxxxxxx
+ * 0000 0080-0000 07FF 110xxxxx 10xxxxxx
+ * 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx
+ *
+ * Check for the 0x110000 limit too
+ */
+ cur = ctxt->input->cur;
+
+ c = *cur;
+ if (c & 0x80) {
+ if (cur[1] == 0)
+ xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
+ if ((cur[1] & 0xc0) != 0x80)
+ goto encoding_error;
+ if ((c & 0xe0) == 0xe0) {
+ unsigned int val;
+
+ if (cur[2] == 0)
+ xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
+ if ((cur[2] & 0xc0) != 0x80)
+ goto encoding_error;
+ if ((c & 0xf0) == 0xf0) {
+ if (cur[3] == 0)
+ xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
+ if (((c & 0xf8) != 0xf0) ||
+ ((cur[3] & 0xc0) != 0x80))
+ goto encoding_error;
+ /* 4-byte code */
+ ctxt->input->cur += 4;
+ val = (cur[0] & 0x7) << 18;
+ val |= (cur[1] & 0x3f) << 12;
+ val |= (cur[2] & 0x3f) << 6;
+ val |= cur[3] & 0x3f;
+ } else {
+ /* 3-byte code */
+ ctxt->input->cur += 3;
+ val = (cur[0] & 0xf) << 12;
+ val |= (cur[1] & 0x3f) << 6;
+ val |= cur[2] & 0x3f;
+ }
+ if (((val > 0xd7ff) && (val < 0xe000)) ||
+ ((val > 0xfffd) && (val < 0x10000)) ||
+ (val >= 0x110000)) {
+ if ((ctxt->sax != NULL) &&
+ (ctxt->sax->error != NULL))
+ ctxt->sax->error(ctxt->userData,
+ "Char 0x%X out of allowed range\n",
+ val);
+ ctxt->errNo = XML_ERR_INVALID_ENCODING;
+ ctxt->wellFormed = 0;
+ if (ctxt->recovery == 0)
+ ctxt->disableSAX = 1;
+ }
+ } else
+ /* 2-byte code */
+ ctxt->input->cur += 2;
+ } else
+ /* 1-byte code */
+ ctxt->input->cur++;
+
+ ctxt->nbChars++;
+ if (*ctxt->input->cur == 0)
+ xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
+ }
} else {
- ctxt->input->cur++;
- ctxt->nbChars++;
- if (*ctxt->input->cur == 0)
- xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
+ /*
+ * Assume it's a fixed length encoding (1) with
+ * a compatible encoding for the ASCII set, since
+ * XML constructs only use < 128 chars
+ */
+
+ if (*(ctxt->input->cur) == '\n') {
+ ctxt->input->line++;
+ ctxt->input->col = 1;
+ } else
+ ctxt->input->col++;
+ ctxt->input->cur++;
+ ctxt->nbChars++;
+ if (*ctxt->input->cur == 0)
+ xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
}
if ((*ctxt->input->cur == '%') && (!ctxt->html))
- xmlParserHandlePEReference(ctxt);
+ xmlParserHandlePEReference(ctxt);
if ((*ctxt->input->cur == 0) &&
(xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0))
- xmlPopInput(ctxt);
+ xmlPopInput(ctxt);
return;
-encoding_error:
+ encoding_error:
/*
* If we detect an UTF8 error that probably mean that the
* input encoding didn't get properly advertised in the
@@ -1217,16 +1228,17 @@
* encoding !)
*/
if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) {
- ctxt->sax->error(ctxt->userData,
- "Input is not proper UTF-8, indicate encoding !\n");
- ctxt->sax->error(ctxt->userData, "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n",
- ctxt->input->cur[0], ctxt->input->cur[1],
- ctxt->input->cur[2], ctxt->input->cur[3]);
+ ctxt->sax->error(ctxt->userData,
+ "Input is not proper UTF-8, indicate encoding !\n");
+ ctxt->sax->error(ctxt->userData,
+ "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n",
+ ctxt->input->cur[0], ctxt->input->cur[1],
+ ctxt->input->cur[2], ctxt->input->cur[3]);
}
ctxt->wellFormed = 0;
ctxt->errNo = XML_ERR_INVALID_ENCODING;
- ctxt->charset = XML_CHAR_ENCODING_8859_1;
+ ctxt->charset = XML_CHAR_ENCODING_8859_1;
ctxt->input->cur++;
return;
}