diff options
author | John Mark Bell <jmb@netsurf-browser.org> | 2008-07-31 14:43:32 +0000 |
---|---|---|
committer | John Mark Bell <jmb@netsurf-browser.org> | 2008-07-31 14:43:32 +0000 |
commit | 6d3950b141b1cdb1f29e929c8c8156562c7ccbc7 (patch) | |
tree | d2bb92960c4c3b54f083f1307241d5fdbac7fdfd /src/input/inputstream.c | |
parent | 2f7a0e956c151c900789a02d8f850bfe79b54071 (diff) | |
download | libhubbub-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/input/inputstream.c')
-rw-r--r-- | src/input/inputstream.c | 481 |
1 files changed, 0 insertions, 481 deletions
diff --git a/src/input/inputstream.c b/src/input/inputstream.c deleted file mode 100644 index 744aa23..0000000 --- a/src/input/inputstream.c +++ /dev/null @@ -1,481 +0,0 @@ -/* - * This file is part of Hubbub. - * Licensed under the MIT License, - * http://www.opensource.org/licenses/mit-license.php - * Copyright 2007 John-Mark Bell <jmb@netsurf-browser.org> - */ - -#include <stdlib.h> - -#include "charset/aliases.h" -#include "input/streamimpl.h" - -/** - * Buffer moving claimant context - */ -struct hubbub_inputstream_bm_handler { - hubbub_inputstream_buffermoved handler; /**< Handler function */ - void *pw; /**< Client private data */ - - struct hubbub_inputstream_bm_handler *next; - struct hubbub_inputstream_bm_handler *prev; -}; - -extern hubbub_streamhandler utf8stream; -extern hubbub_streamhandler utf16stream; - -static hubbub_streamhandler *handler_table[] = { - &utf8stream, - &utf16stream, - NULL -}; - -/** - * Create an input stream - * - * \param enc Document charset, or NULL to autodetect - * \param int_enc Desired encoding of document - * \param alloc Memory (de)allocation function - * \param pw Pointer to client-specific private data (may be NULL) - * \return Pointer to stream instance, or NULL on failure - */ -hubbub_inputstream *hubbub_inputstream_create(const char *enc, - const char *int_enc, hubbub_alloc alloc, void *pw) -{ - hubbub_inputstream *stream; - hubbub_streamhandler **handler; - - if (int_enc == NULL || alloc == NULL) - return NULL; - - /* Search for handler class */ - for (handler = handler_table; *handler != NULL; handler++) { - if ((*handler)->uses_encoding(int_enc)) - break; - } - - /* None found */ - if ((*handler) == NULL) - return NULL; - - stream = (*handler)->create(enc, int_enc, alloc, pw); - if (stream == NULL) - return NULL; - - stream->handlers = NULL; - - stream->alloc = alloc; - stream->pw = pw; - - return stream; -} - -/** - * Destroy an input stream - * - * \param stream Input stream to destroy - */ -void hubbub_inputstream_destroy(hubbub_inputstream *stream) -{ - hubbub_inputstream_bm_handler *h, *i; - - if (stream == NULL) - return; - - for (h = stream->handlers; h; h = i) { - i = h->next; - - stream->alloc(h, 0, stream->pw); - } - - stream->destroy(stream); -} - -/** - * Append data to an input stream - * - * \param stream Input stream to append data to - * \param data Data to append (in document charset), or NULL to flag EOF - * \param len Length, in bytes, of data - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_inputstream_append(hubbub_inputstream *stream, - const uint8_t *data, size_t len) -{ - if (stream == NULL) - return HUBBUB_BADPARM; - - /* Calling this if we've disowned the buffer is foolish */ - if (stream->buffer == NULL) - return HUBBUB_INVALID; - - return stream->append(stream, data, len); -} - -/** - * Insert data into stream at current location - * - * \param stream Input stream to insert into - * \param data Data to insert (UTF-8 encoded) - * \param len Length, in bytes, of data - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_inputstream_insert(hubbub_inputstream *stream, - const uint8_t *data, size_t len) -{ - if (stream == NULL || data == NULL) - return HUBBUB_BADPARM; - - /* Calling this if we've disowned the buffer is foolish */ - if (stream->buffer == NULL) - return HUBBUB_INVALID; - - return stream->insert(stream, data, len); -} - -/** - * Look at the next character in the stream - * - * \param stream Stream to look in - * \return UCS4 (host-endian) character code, or EOF or OOD. - */ -uint32_t hubbub_inputstream_peek(hubbub_inputstream *stream) -{ - /* It is illegal to call this after the buffer has been disowned */ - if (stream == NULL || stream->buffer == NULL) - return HUBBUB_INPUTSTREAM_OOD; - - return stream->peek(stream);; -} - -/** - * Retrieve the byte index and length of the current character in the stream - * - * \param stream Stream to look in - * \param len Pointer to location to receive byte length of character - * \return Byte index of current character from start of stream, - * or (uint32_t) -1 on error - */ -uint32_t hubbub_inputstream_cur_pos(hubbub_inputstream *stream, - size_t *len) -{ - /* It is illegal to call this after the buffer has been disowned */ - if (stream == NULL || len == NULL || stream->buffer == NULL) - return (uint32_t) -1; - - return stream->cur_pos(stream, len); -} - -/** - * Convert the current character to lower case - * - * \param stream Stream to look in - */ -void hubbub_inputstream_lowercase(hubbub_inputstream *stream) -{ - if (stream == NULL || stream->buffer == NULL) - return; - - stream->lowercase(stream); -} - -/** - * Convert the current character to upper case - * - * \param stream Stream to look in - */ -void hubbub_inputstream_uppercase(hubbub_inputstream *stream) -{ - if (stream == NULL || stream->buffer == NULL) - return; - - stream->uppercase(stream); -} - -/** - * Advance the stream's current position - * - * \param stream The stream whose position to advance - */ -void hubbub_inputstream_advance(hubbub_inputstream *stream) -{ - /* It is illegal to call this after the buffer has been disowned */ - if (stream == NULL || stream->buffer == NULL) - return; - - if (stream->cursor == stream->buffer_len) - return; - - stream->advance(stream); -} - -/** - * Push a character back onto the stream - * - * \param stream Stream to push back to - * \param character UCS4 (host-endian) codepoint to push back - * \return HUBBUB_OK on success, appropriate error otherwise - * - * Note that this doesn't actually modify the data in the stream. - * It works by ensuring that the character located just before the - * current stream location is the same as ::character. If it is, - * then the stream pointer is moved back. If it is not, then an - * error is returned and the stream pointer remains unmodified. - */ -hubbub_error hubbub_inputstream_push_back(hubbub_inputstream *stream, - uint32_t character) -{ - /* It is illegal to call this after the buffer has been disowned */ - if (stream == NULL || stream->buffer == NULL) - return HUBBUB_BADPARM; - - if (stream->cursor == 0) - return HUBBUB_INVALID; - - return stream->push_back(stream, character); -} - -/** - * Rewind the input stream by a number of bytes - * - * \param stream Stream to rewind - * \param n Number of bytes to go back - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_inputstream_rewind(hubbub_inputstream *stream, size_t n) -{ - if (stream == NULL || stream->buffer == NULL) - return HUBBUB_BADPARM; - - if (stream->cursor < n) - return HUBBUB_INVALID; - - stream->cursor -= n; - - return HUBBUB_OK; -} - -/** - * Claim ownership of an input stream's buffer - * - * \param stream Input stream whose buffer to claim - * \param buffer Pointer to location to receive buffer pointer - * \param len Pointer to location to receive byte length of buffer - * \return HUBBUB_OK on success, appropriate error otherwise. - * - * Once the buffer has been claimed by a client, the input stream disclaims - * all ownership rights (and invalidates any internal references it may have - * to the buffer). Therefore, the only input stream call which may be made - * after calling this function is to destroy the input stream. Therefore, - * unless the stream pointer is located at EOF, this call will return an - * error. - */ -hubbub_error hubbub_inputstream_claim_buffer(hubbub_inputstream *stream, - uint8_t **buffer, size_t *len) -{ - if (stream == NULL || buffer == NULL || len == NULL) - return HUBBUB_BADPARM; - - if (stream->had_eof == false || - stream->cursor != stream->buffer_len) - return HUBBUB_INVALID; - - *buffer = stream->buffer; - *len = stream->buffer_len; - - stream->buffer = NULL; - - return HUBBUB_OK; -} - -/** - * Register interest in buffer moved events - * - * \param stream Input stream to register interest with - * \param handler Pointer to handler function - * \param pw Pointer to client-specific private data (may be NULL) - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_inputstream_register_movehandler( - hubbub_inputstream *stream, - hubbub_inputstream_buffermoved handler, void *pw) -{ - hubbub_inputstream_bm_handler *h; - - if (stream == NULL || handler == NULL) - return HUBBUB_BADPARM; - - h = stream->alloc(NULL, sizeof(hubbub_inputstream_bm_handler), - stream->pw); - if (h == NULL) - return HUBBUB_NOMEM; - - h->handler = handler; - h->pw = pw; - - h->prev = NULL; - h->next = stream->handlers; - - if (stream->handlers) - stream->handlers->prev = h; - stream->handlers = h; - - /* And notify claimant of current buffer location */ - handler(stream->buffer, stream->buffer_len, pw); - - return HUBBUB_OK; -} - -/** - * Deregister interest in buffer moved events - * - * \param stream Input stream to deregister from - * \param handler Pointer to handler function - * \param pw Pointer to client-specific private data (may be NULL) - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_inputstream_deregister_movehandler( - hubbub_inputstream *stream, - hubbub_inputstream_buffermoved handler, void *pw) -{ - hubbub_inputstream_bm_handler *h; - - if (stream == NULL || handler == NULL) - return HUBBUB_BADPARM; - - for (h = stream->handlers; h; h = h->next) { - if (h->handler == handler && h->pw == pw) - break; - } - - if (h == NULL) - return HUBBUB_INVALID; - - if (h->next) - h->next->prev = h->prev; - if (h->prev) - h->prev->next = h->next; - else - stream->handlers = h->next; - - stream->alloc(h, 0, stream->pw); - - return HUBBUB_OK; -} - -/** - * Case insensitively compare a pair of ranges in the input stream - * - * \param stream Input stream to look in - * \param r1 Offset of start of first range - * \param r2 Offset of start of second range - * \param len Byte length of ranges - * \return 0 if ranges match, non-zero otherwise - */ -int hubbub_inputstream_compare_range_ci(hubbub_inputstream *stream, - uint32_t r1, uint32_t r2, size_t len) -{ - if (stream == NULL || stream->buffer == NULL) - return 1; /* arbitrary */ - - return stream->cmp_range_ci(stream, r1, r2, len); -} - -/** - * Case sensitively compare a pair of ranges in the input stream - * - * \param stream Input stream to look in - * \param r1 Offset of start of first range - * \param r2 Offset of start of second range - * \param len Byte length of ranges - * \return 0 if ranges match, non-zero otherwise - */ -int hubbub_inputstream_compare_range_cs(hubbub_inputstream *stream, - uint32_t r1, uint32_t r2, size_t len) -{ - if (stream == NULL || stream->buffer == NULL) - return 1; /* arbitrary */ - - return stream->cmp_range_cs(stream, r1, r2, len); -} - -/** - * Case sensitively compare a range of input stream against an ASCII string - * - * \param stream Input stream to look in - * \param off Offset of range start - * \param len Byte length of range - * \param data Comparison string - * \param dlen Byte length of comparison string - * \return 0 if match, non-zero otherwise - */ -int hubbub_inputstream_compare_range_ascii(hubbub_inputstream *stream, - uint32_t off, size_t len, const char *data, size_t dlen) -{ - if (stream == NULL || stream->buffer == NULL) - return 1; /* arbitrary */ - - return stream->cmp_range_ascii(stream, off, len, data, dlen); -} - -/** - * Replace a range of bytes in the input stream with a single character - * - * \param stream Input stream containing data - * \param start Offset of start of range to replace - * \param len Length (in bytes) of range to replace - * \param ucs4 UCS4 (host endian) encoded replacement character - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_inputstream_replace_range(hubbub_inputstream *stream, - uint32_t start, size_t len, uint32_t ucs4) -{ - if (stream == NULL || stream->buffer == NULL) - return HUBBUB_BADPARM; - - if (start >= stream->buffer_len) - return HUBBUB_INVALID; - - if (start < stream->cursor) - return HUBBUB_INVALID; - - return stream->replace_range(stream, start, len, ucs4); -} - -/** - * Read the document charset - * - * \param stream Input stream to query - * \param source Pointer to location to receive charset source - * \return Pointer to charset name (constant; do not free), or NULL if unknown - */ -const char *hubbub_inputstream_read_charset(hubbub_inputstream *stream, - hubbub_charset_source *source) -{ - if (stream == NULL || source == NULL) - return NULL; - - *source = stream->encsrc; - - if (stream->encsrc == HUBBUB_CHARSET_UNKNOWN) - return NULL; - - return hubbub_mibenum_to_name(stream->mibenum); -} - -/** - * Inform interested parties that the buffer has moved - * - * \param stream Input stream - */ -void hubbub_inputstream_buffer_moved(hubbub_inputstream *stream) -{ - hubbub_inputstream_bm_handler *h; - - if (stream == NULL) - return; - - for (h = stream->handlers; h; h = h->next) - h->handler(stream->buffer, stream->buffer_len, h->pw); -} - |