summaryrefslogtreecommitdiff
path: root/src/charset/detect.c
diff options
context:
space:
mode:
authorJohn Mark Bell <jmb@netsurf-browser.org>2008-07-31 14:43:32 +0000
committerJohn Mark Bell <jmb@netsurf-browser.org>2008-07-31 14:43:32 +0000
commit6d3950b141b1cdb1f29e929c8c8156562c7ccbc7 (patch)
treed2bb92960c4c3b54f083f1307241d5fdbac7fdfd /src/charset/detect.c
parent2f7a0e956c151c900789a02d8f850bfe79b54071 (diff)
downloadlibhubbub-6d3950b141b1cdb1f29e929c8c8156562c7ccbc7.tar.gz
libhubbub-6d3950b141b1cdb1f29e929c8c8156562c7ccbc7.tar.bz2
Merged revisions 4631-4838 via svnmerge from
svn://source.netsurf-browser.org/branches/takkaria/hubbub-parserutils ........ r4631 | takkaria | 2008-07-13 12:54:30 +0100 (Sun, 13 Jul 2008) | 2 lines Initial hatchet job moving to libparserutils (search and replace and a bit of cleaning up). This doesn't compile. ........ r4632 | takkaria | 2008-07-13 15:28:52 +0100 (Sun, 13 Jul 2008) | 2 lines libparserutilize everything up to the "before attribute name" state. (Not compiling) ........ r4633 | takkaria | 2008-07-13 15:32:14 +0100 (Sun, 13 Jul 2008) | 2 lines Replace all uses of "current_{comment|chars}" with just "chars". ........ r4634 | takkaria | 2008-07-13 16:12:06 +0100 (Sun, 13 Jul 2008) | 2 lines Fix lots of compile errors, lpuise "before attribute name" state. ........ r4636 | takkaria | 2008-07-13 17:23:17 +0100 (Sun, 13 Jul 2008) | 2 lines Finish lpuising the tag states, apart from character references. ........ r4637 | takkaria | 2008-07-13 19:58:52 +0100 (Sun, 13 Jul 2008) | 2 lines lpuise the comment states. ........ r4638 | takkaria | 2008-07-13 20:04:31 +0100 (Sun, 13 Jul 2008) | 2 lines Switch to setting hubbub_string::len to 0 instead of hubbub_string::ptr to NULL to indicate an empty buffer, as it was previously. ........ r4639 | takkaria | 2008-07-13 21:02:11 +0100 (Sun, 13 Jul 2008) | 2 lines "lpu up" about half of the DOCTYPE handling stages. ........ r4640 | takkaria | 2008-07-13 21:23:00 +0100 (Sun, 13 Jul 2008) | 2 lines Finish off LPUing the doctype modes. ........ r4641 | takkaria | 2008-07-13 21:37:33 +0100 (Sun, 13 Jul 2008) | 2 lines The tokeniser uses lpu apart from the entity matcher, now. ........ r4643 | takkaria | 2008-07-14 01:20:36 +0100 (Mon, 14 Jul 2008) | 2 lines Fix up the character reference matching stuff--still not properly dealt with, but compiles futher. ........ r4644 | takkaria | 2008-07-14 01:24:49 +0100 (Mon, 14 Jul 2008) | 2 lines Get the tokeniser compiling in its LPU'd form. ........ r4645 | takkaria | 2008-07-14 01:26:34 +0100 (Mon, 14 Jul 2008) | 2 lines Remember to advance the stream position after emitting tokens. ........ r4646 | takkaria | 2008-07-14 01:34:36 +0100 (Mon, 14 Jul 2008) | 2 lines Nuke the src/input directory and start work on the treebuilder. ........ r4647 | takkaria | 2008-07-14 01:56:27 +0100 (Mon, 14 Jul 2008) | 2 lines Get hubbub building in its LPU'd form. ........ r4648 | takkaria | 2008-07-14 02:41:03 +0100 (Mon, 14 Jul 2008) | 2 lines Get the tokeniser2 testrunner working. ........ r4649 | takkaria | 2008-07-14 02:48:55 +0100 (Mon, 14 Jul 2008) | 2 lines Fix test LDFLAGS so things link properly. ........ r4650 | takkaria | 2008-07-14 16:25:51 +0100 (Mon, 14 Jul 2008) | 2 lines Get testcases compiling, remove ones now covered by libparserutils. ........ r4651 | takkaria | 2008-07-14 16:37:09 +0100 (Mon, 14 Jul 2008) | 2 lines Remove more tests covered by libpu. ........ r4652 | takkaria | 2008-07-14 17:53:18 +0100 (Mon, 14 Jul 2008) | 2 lines Fix up the tokeniser a bit. ........ r4653 | takkaria | 2008-07-14 19:02:15 +0100 (Mon, 14 Jul 2008) | 3 lines - Remove the buffer_handler stuff from hubbub - Add the basics of a buffer for attribute values and text. ........ r4654 | takkaria | 2008-07-14 20:00:45 +0100 (Mon, 14 Jul 2008) | 2 lines Get character references working in attribute values, start trying to make them work in character tokens. ........ r4656 | takkaria | 2008-07-14 23:28:52 +0100 (Mon, 14 Jul 2008) | 2 lines Get entities working a bit better. ........ r4657 | takkaria | 2008-07-14 23:37:16 +0100 (Mon, 14 Jul 2008) | 2 lines Get entities working properly. (!) ........ r4658 | takkaria | 2008-07-14 23:56:10 +0100 (Mon, 14 Jul 2008) | 2 lines Make doctypes work a bit better. ........ r4659 | takkaria | 2008-07-15 00:18:49 +0100 (Tue, 15 Jul 2008) | 2 lines Get DOCTYPEs working. ........ r4660 | takkaria | 2008-07-15 00:26:36 +0100 (Tue, 15 Jul 2008) | 2 lines Fix CDATA sections. ........ r4661 | takkaria | 2008-07-15 01:01:16 +0100 (Tue, 15 Jul 2008) | 2 lines Get comments working again. ........ r4662 | takkaria | 2008-07-15 01:14:19 +0100 (Tue, 15 Jul 2008) | 2 lines Fix EOF in "after attribute name" state. ........ r4664 | takkaria | 2008-07-15 01:30:27 +0100 (Tue, 15 Jul 2008) | 2 lines Put the tests in better order, remove one now superceded with libpu. ........ r4665 | takkaria | 2008-07-15 01:46:29 +0100 (Tue, 15 Jul 2008) | 2 lines Remove a lot of now-redunant clearings of the current stream offset. ........ r4667 | jmb | 2008-07-15 11:56:54 +0100 (Tue, 15 Jul 2008) | 2 lines Completely purge charset stuff from hubbub. Parserutils handles this now. ........ r4677 | takkaria | 2008-07-15 21:03:42 +0100 (Tue, 15 Jul 2008) | 2 lines Get more tests passing, handle NUL bytes in data state. ........ r4694 | takkaria | 2008-07-18 17:55:44 +0100 (Fri, 18 Jul 2008) | 3 lines - Handle CRs correctly in some token states. - Handle NULs correctly in the CDATA state. ........ r4706 | takkaria | 2008-07-19 14:58:48 +0100 (Sat, 19 Jul 2008) | 2 lines Improve the tokeniser2 output a bit. ........ r4721 | takkaria | 2008-07-21 20:57:29 +0100 (Mon, 21 Jul 2008) | 2 lines Get a better framework in place to allow switching to using a buffer mid-collect. This fails a couple of testcases and doesn't implement proper CR or NUL support yet. ........ r4725 | takkaria | 2008-07-23 17:20:07 +0100 (Wed, 23 Jul 2008) | 2 lines Make comment tokens in tokeniser2 display both expected and actual output. ........ r4726 | takkaria | 2008-07-23 19:10:23 +0100 (Wed, 23 Jul 2008) | 4 lines - Add FINISH() macro which stops using buffered character collection. - Make the encoding U+FFFD in UTF-8 a global varabile, for sanity - Make the bogus comment state deal with NULs correctly. ........ r4730 | takkaria | 2008-07-24 00:35:16 +0100 (Thu, 24 Jul 2008) | 2 lines Try to get NUL bytes handled as the spec says. ........ r4731 | takkaria | 2008-07-24 00:40:59 +0100 (Thu, 24 Jul 2008) | 2 lines Get CRs working in the data state. ........ r4732 | takkaria | 2008-07-24 00:47:45 +0100 (Thu, 24 Jul 2008) | 2 lines Set force-quirks correctly when failing to match PUBLIC or SYSTEM in DOCTYPEs. ........ r4773 | takkaria | 2008-07-28 15:34:41 +0100 (Mon, 28 Jul 2008) | 2 lines Fix up the tokeniser, finally. ........ r4801 | takkaria | 2008-07-29 15:59:31 +0100 (Tue, 29 Jul 2008) | 2 lines Refactor macros a bit. ........ r4802 | takkaria | 2008-07-29 16:04:17 +0100 (Tue, 29 Jul 2008) | 2 lines Do s/HUBBUB_TOKENISER_STATE_/STATE_/, for shorter line lengths. ........ r4805 | takkaria | 2008-07-29 16:58:37 +0100 (Tue, 29 Jul 2008) | 4 lines Start cleaning up the hubbub tokeniser; - refactor to use new inline emit_character_token() and emit_current_tag() functions; makes code clearer - check EOF before using the CHAR() macro, so eventually it can be removed. ........ r4806 | takkaria | 2008-07-29 17:45:36 +0100 (Tue, 29 Jul 2008) | 2 lines More cleanup like the previous commit. ........ r4807 | takkaria | 2008-07-29 19:48:44 +0100 (Tue, 29 Jul 2008) | 2 lines Rewrite comment-handling code to be just the one function, whilst updating it to handle CRs and NULs properly. (All comments now always use the buffer.) ........ r4820 | takkaria | 2008-07-30 14:14:49 +0100 (Wed, 30 Jul 2008) | 2 lines Finish off the first sweep of cleaning up and refactoring the tokeniser. ........ r4821 | takkaria | 2008-07-30 15:12:22 +0100 (Wed, 30 Jul 2008) | 2 lines Add copyright statement. ........ r4822 | takkaria | 2008-07-30 17:23:01 +0100 (Wed, 30 Jul 2008) | 2 lines Apply changes made to tokeniser2 to tokeniser3. ........ r4829 | takkaria | 2008-07-31 01:59:07 +0100 (Thu, 31 Jul 2008) | 4 lines - Make the tokeniser save everything into the buffer, at least for now. - Fix logic errors introduced in refactoring - Avoid emitting more tokens than we have to (e.g. instead of emitting "<>" and switching back to the data state, just switch back to the data state and let it take care of it) ........ r4830 | takkaria | 2008-07-31 02:03:08 +0100 (Thu, 31 Jul 2008) | 2 lines Small treebuilder <isindex> fix. ........ r4831 | takkaria | 2008-07-31 02:32:29 +0100 (Thu, 31 Jul 2008) | 2 lines Stop holding on to pointers to character data across treebuilder calls. ........ r4832 | takkaria | 2008-07-31 02:45:09 +0100 (Thu, 31 Jul 2008) | 18 lines Merge revisions 4620-4831 from trunk hubbub to libinputstream hubbub, modulo one change to test/Makefile which makes the linker choke when linking tests. ------------------------------------------------------------------------ r4666 | jmb | 2008-07-15 11:52:13 +0100 (Tue, 15 Jul 2008) | 3 lines Make tree2 perform reference counting. Fix bits of the treebuilder to perform reference counting correctly in the face of *result not pointing to the same object as the node passed in to the treebuilder client callbacks. ------------------------------------------------------------------------ r4668 | jmb | 2008-07-15 12:37:30 +0100 (Tue, 15 Jul 2008) | 2 lines Fully document treebuilder callbacks. ------------------------------------------------------------------------ r4675 | takkaria | 2008-07-15 21:01:03 +0100 (Tue, 15 Jul 2008) | 2 lines Fix memory leak in tokeniser2. ------------------------------------------------------------------------ ........ r4834 | jmb | 2008-07-31 09:57:51 +0100 (Thu, 31 Jul 2008) | 2 lines Fix infinite loop in charset detector ........ r4835 | jmb | 2008-07-31 13:01:24 +0100 (Thu, 31 Jul 2008) | 2 lines Actually store namespaces on formatting list. Otherwise we read uninitialised memory. Add some semblance of filling allocations with junk to myrealloc(). ........ r4836 | jmb | 2008-07-31 13:06:07 +0100 (Thu, 31 Jul 2008) | 2 lines Lose debug again ........ r4837 | jmb | 2008-07-31 15:09:19 +0100 (Thu, 31 Jul 2008) | 2 lines Lose obsolete testdata (this is now part of lpu) ........ svn path=/trunk/hubbub/; revision=4839
Diffstat (limited to 'src/charset/detect.c')
-rw-r--r--src/charset/detect.c153
1 files changed, 65 insertions, 88 deletions
diff --git a/src/charset/detect.c b/src/charset/detect.c
index 8ff3b87..768eb9a 100644
--- a/src/charset/detect.c
+++ b/src/charset/detect.c
@@ -8,12 +8,15 @@
#include <stdbool.h>
#include <string.h>
-#include "charset/aliases.h"
+#include <parserutils/charset/mibenum.h>
+
+#include <hubbub/types.h>
+
#include "utils/utils.h"
#include "detect.h"
-static uint16_t hubbub_charset_read_bom(const uint8_t **data, size_t *len);
+static uint16_t hubbub_charset_read_bom(const uint8_t *data, size_t len);
static uint16_t hubbub_charset_scan_meta(const uint8_t *data, size_t len);
static uint16_t hubbub_charset_parse_attributes(const uint8_t **pos,
const uint8_t *end);
@@ -27,31 +30,31 @@ static bool hubbub_charset_get_attribute(const uint8_t **data,
/**
* Extract a charset from a chunk of data
*
- * \param data Pointer to pointer to buffer containing data
- * \param len Pointer to buffer length
- * \param mibenum Pointer to location to store MIB enum representing charset
- * \param source Pointer to location to receive charset source
- * \return HUBBUB_OK on success, appropriate error otherwise
+ * \param data Pointer to buffer containing data
+ * \param len Buffer length
+ * \param mibenum Pointer to location containing current MIB enum
+ * \param source Pointer to location containint current charset source
+ * \return PARSERUTILS_OK on success, appropriate error otherwise
*
- * The data pointer and length will be modified by this function if
- * a byte order mark is encountered at the start of the buffer. The updated
- * data pointer will point to the first byte in the buffer after the BOM.
- * The length will be modified appropriately.
+ * ::mibenum and ::source will be updated on exit
*
* The larger a chunk of data fed to this routine, the better, as it allows
* charset autodetection access to a larger dataset for analysis.
*/
-hubbub_error hubbub_charset_extract(const uint8_t **data, size_t *len,
- uint16_t *mibenum, hubbub_charset_source *source)
+parserutils_error hubbub_charset_extract(const uint8_t *data, size_t len,
+ uint16_t *mibenum, uint32_t *source)
{
uint16_t charset = 0;
- if (data == NULL || *data == NULL || len == NULL ||
- mibenum == NULL || source == NULL)
- return HUBBUB_BADPARM;
+ if (data == NULL || mibenum == NULL || source == NULL)
+ return PARSERUTILS_BADPARM;
+
+ /* If the source is dictated, there's nothing for us to do */
+ if (*source == HUBBUB_CHARSET_DICTATED)
+ return PARSERUTILS_OK;
/* We need at least 4 bytes of data */
- if (*len < 4)
+ if (len < 4)
goto default_encoding;
/* First, look for a BOM */
@@ -60,21 +63,21 @@ hubbub_error hubbub_charset_extract(const uint8_t **data, size_t *len,
*mibenum = charset;
*source = HUBBUB_CHARSET_DOCUMENT;
- return HUBBUB_OK;
+ return PARSERUTILS_OK;
}
/* No BOM was found, so we must look for a meta charset within
* the document itself. */
- charset = hubbub_charset_scan_meta(*data, *len);
+ charset = hubbub_charset_scan_meta(data, len);
if (charset != 0) {
/* ISO-8859-1 becomes Windows-1252 */
- if (charset == hubbub_mibenum_from_name("ISO-8859-1",
- SLEN("ISO-8859-1"))) {
- charset = hubbub_mibenum_from_name("Windows-1252",
- SLEN("Windows-1252"));
+ if (charset == parserutils_charset_mibenum_from_name(
+ "ISO-8859-1", SLEN("ISO-8859-1"))) {
+ charset = parserutils_charset_mibenum_from_name(
+ "Windows-1252", SLEN("Windows-1252"));
/* Fallback to 8859-1 if that failed */
if (charset == 0)
- charset = hubbub_mibenum_from_name(
+ charset = parserutils_charset_mibenum_from_name(
"ISO-8859-1", SLEN("ISO-8859-1"));
}
@@ -94,23 +97,23 @@ hubbub_error hubbub_charset_extract(const uint8_t **data, size_t *len,
* autodetection routines (or the fallback case if they
* fail).
*/
- if (charset != hubbub_mibenum_from_name("UTF-16",
+ if (charset != parserutils_charset_mibenum_from_name("UTF-16",
SLEN("UTF-16")) &&
- charset != hubbub_mibenum_from_name("UTF-16LE",
- SLEN("UTF-16LE")) &&
- charset != hubbub_mibenum_from_name("UTF-16BE",
- SLEN("UTF-16BE")) &&
- charset != hubbub_mibenum_from_name("UTF-32",
- SLEN("UTF-32")) &&
- charset != hubbub_mibenum_from_name("UTF-32LE",
- SLEN("UTF-32LE")) &&
- charset != hubbub_mibenum_from_name("UTF-32BE",
- SLEN("UTF-32BE"))) {
+ charset != parserutils_charset_mibenum_from_name(
+ "UTF-16LE", SLEN("UTF-16LE")) &&
+ charset != parserutils_charset_mibenum_from_name(
+ "UTF-16BE", SLEN("UTF-16BE")) &&
+ charset != parserutils_charset_mibenum_from_name(
+ "UTF-32", SLEN("UTF-32")) &&
+ charset != parserutils_charset_mibenum_from_name(
+ "UTF-32LE", SLEN("UTF-32LE")) &&
+ charset != parserutils_charset_mibenum_from_name(
+ "UTF-32BE", SLEN("UTF-32BE"))) {
*mibenum = charset;
*source = HUBBUB_CHARSET_DOCUMENT;
- return HUBBUB_OK;
+ return PARSERUTILS_OK;
}
}
@@ -122,16 +125,16 @@ hubbub_error hubbub_charset_extract(const uint8_t **data, size_t *len,
/* We failed to autodetect a charset, so use the default fallback */
default_encoding:
- charset = hubbub_mibenum_from_name("Windows-1252",
+ charset = parserutils_charset_mibenum_from_name("Windows-1252",
SLEN("Windows-1252"));
if (charset == 0)
- charset = hubbub_mibenum_from_name("ISO-8859-1",
+ charset = parserutils_charset_mibenum_from_name("ISO-8859-1",
SLEN("ISO-8859-1"));
*mibenum = charset;
*source = HUBBUB_CHARSET_DEFAULT;
- return HUBBUB_OK;
+ return PARSERUTILS_OK;
}
@@ -139,65 +142,38 @@ default_encoding:
* Inspect the beginning of a buffer of data for the presence of a
* UTF Byte Order Mark.
*
- * \param data Pointer to pointer to buffer containing data
- * \param len Pointer to buffer length
+ * \param data Pointer to buffer containing data
+ * \param len Buffer length
* \return MIB enum representing encoding described by BOM, or 0 if not found
- *
- * If a BOM is found, the data pointer will be modified to point to the first
- * byte in the buffer after the BOM. The length will also be modified
- * appropriately.
*/
-uint16_t hubbub_charset_read_bom(const uint8_t **data, size_t *len)
+uint16_t hubbub_charset_read_bom(const uint8_t *data, size_t len)
{
- if (data == NULL || *data == NULL || len == NULL)
+ if (data == NULL)
return 0;
/* We require at least 4 bytes of data */
- if (*len < 4)
+ if (len < 4)
return 0;
-#define UTF32BOM_LEN (4)
-#define UTF16BOM_LEN (2)
-#define UTF8BOM_LEN (3)
-
- if ((*data)[0] == 0x00 && (*data)[1] == 0x00 &&
- (*data)[2] == 0xFE && (*data)[3] == 0xFF) {
- *data += UTF32BOM_LEN;
- *len -= UTF32BOM_LEN;
-
- return hubbub_mibenum_from_name("UTF-32BE",
+ if (data[0] == 0x00 && data[1] == 0x00 &&
+ data[2] == 0xFE && data[3] == 0xFF) {
+ return parserutils_charset_mibenum_from_name("UTF-32BE",
SLEN("UTF-32BE"));
- } else if ((*data)[0] == 0xFF && (*data)[1] == 0xFE &&
- (*data)[2] == 0x00 && (*data)[3] == 0x00) {
- *data += UTF32BOM_LEN;
- *len -= UTF32BOM_LEN;
-
- return hubbub_mibenum_from_name("UTF-32LE",
+ } else if (data[0] == 0xFF && data[1] == 0xFE &&
+ data[2] == 0x00 && data[3] == 0x00) {
+ return parserutils_charset_mibenum_from_name("UTF-32LE",
SLEN("UTF-32LE"));
- } else if ((*data)[0] == 0xFE && (*data)[1] == 0xFF) {
- *data += UTF16BOM_LEN;
- *len -= UTF16BOM_LEN;
-
- return hubbub_mibenum_from_name("UTF-16BE",
+ } else if (data[0] == 0xFE && data[1] == 0xFF) {
+ return parserutils_charset_mibenum_from_name("UTF-16BE",
SLEN("UTF-16BE"));
- } else if ((*data)[0] == 0xFF && (*data)[1] == 0xFE) {
- *data += UTF16BOM_LEN;
- *len -= UTF16BOM_LEN;
-
- return hubbub_mibenum_from_name("UTF-16LE",
+ } else if (data[0] == 0xFF && data[1] == 0xFE) {
+ return parserutils_charset_mibenum_from_name("UTF-16LE",
SLEN("UTF-16LE"));
- } else if ((*data)[0] == 0xEF && (*data)[1] == 0xBB &&
- (*data)[2] == 0xBF) {
- *data += UTF8BOM_LEN;
- *len -= UTF8BOM_LEN;
-
- return hubbub_mibenum_from_name("UTF-8", SLEN("UTF-8"));
+ } else if (data[0] == 0xEF && data[1] == 0xBB && data[2] == 0xBF) {
+ return parserutils_charset_mibenum_from_name("UTF-8",
+ SLEN("UTF-8"));
}
-#undef UTF32BOM_LEN
-#undef UTF16BOM_LEN
-#undef UTF8BOM_LEN
-
return 0;
}
@@ -223,7 +199,7 @@ uint16_t hubbub_charset_read_bom(const uint8_t **data, size_t *len)
* Search for a meta charset within a buffer of data
*
* \param data Pointer to buffer containing data
- * \param len Length of buffer in data
+ * \param len Length of buffer
* \return MIB enum representing encoding, or 0 if none found
*/
uint16_t hubbub_charset_scan_meta(const uint8_t *data, size_t len)
@@ -344,7 +320,7 @@ uint16_t hubbub_charset_parse_attributes(const uint8_t **pos,
while (valuelen > 0 && ISSPACE(value[valuelen - 1]))
valuelen--;
- mibenum = hubbub_mibenum_from_name(
+ mibenum = parserutils_charset_mibenum_from_name(
(const char *) value, valuelen);
if (mibenum != 0)
return mibenum;
@@ -478,8 +454,8 @@ uint16_t hubbub_charset_parse_content(const uint8_t *value,
/* 8 */
if (tentative != NULL) {
- return hubbub_mibenum_from_name((const char *) tentative,
- tentative_len);
+ return parserutils_charset_mibenum_from_name(
+ (const char *) tentative, tentative_len);
}
/* 9 */
@@ -555,6 +531,7 @@ bool hubbub_charset_get_attribute(const uint8_t **data, const uint8_t *end,
/* c */
if (*pos == '/' || *pos == '<' || *pos == '>') {
+ *data = pos;
return true;
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-04-24 11:33:54 +0000