From 6d3950b141b1cdb1f29e929c8c8156562c7ccbc7 Mon Sep 17 00:00:00 2001 From: John Mark Bell Date: Thu, 31 Jul 2008 14:43:32 +0000 Subject: 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 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 --- src/charset/codec.c | 188 ---------------------------------------------------- 1 file changed, 188 deletions(-) delete mode 100644 src/charset/codec.c (limited to 'src/charset/codec.c') diff --git a/src/charset/codec.c b/src/charset/codec.c deleted file mode 100644 index 727d600..0000000 --- a/src/charset/codec.c +++ /dev/null @@ -1,188 +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 - */ - -#include - -#include "charset/aliases.h" - -#include "codec_impl.h" - -extern hubbub_charsethandler hubbub_iconv_codec_handler; -extern hubbub_charsethandler hubbub_utf8_codec_handler; -extern hubbub_charsethandler hubbub_utf16_codec_handler; - -static hubbub_charsethandler *handler_table[] = { - &hubbub_utf8_codec_handler, - &hubbub_utf16_codec_handler, - &hubbub_iconv_codec_handler, - NULL, -}; - -/** - * Create a charset codec - * - * \param charset Target charset - * \param alloc Memory (de)allocation function - * \param pw Pointer to client-specific private data (may be NULL) - * \return Pointer to codec instance, or NULL on failure - */ -hubbub_charsetcodec *hubbub_charsetcodec_create(const char *charset, - hubbub_alloc alloc, void *pw) -{ - hubbub_charsetcodec *codec; - hubbub_charsethandler **handler; - const hubbub_aliases_canon * canon; - - if (charset == NULL || alloc == NULL) - return NULL; - - /* Canonicalise charset name. */ - canon = hubbub_alias_canonicalise(charset, strlen(charset)); - if (canon == NULL) - return NULL; - - /* Search for handler class */ - for (handler = handler_table; *handler != NULL; handler++) { - if ((*handler)->handles_charset(canon->name)) - break; - } - - /* None found */ - if ((*handler) == NULL) - return NULL; - - /* Instantiate class */ - codec = (*handler)->create(canon->name, alloc, pw); - if (codec == NULL) - return NULL; - - /* and initialise it */ - codec->mibenum = canon->mib_enum; - - codec->filter = NULL; - codec->filter_pw = NULL; - - codec->errormode = HUBBUB_CHARSETCODEC_ERROR_LOOSE; - - codec->alloc = alloc; - codec->alloc_pw = pw; - - return codec; -} - -/** - * Destroy a charset codec - * - * \param codec The codec to destroy - */ -void hubbub_charsetcodec_destroy(hubbub_charsetcodec *codec) -{ - if (codec == NULL) - return; - - codec->handler.destroy(codec); - - codec->alloc(codec, 0, codec->alloc_pw); -} - -/** - * Configure a charset codec - * - * \param codec The codec to configure - * \parem type The codec option type to configure - * \param params Option-specific parameters - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_charsetcodec_setopt(hubbub_charsetcodec *codec, - hubbub_charsetcodec_opttype type, - hubbub_charsetcodec_optparams *params) -{ - if (codec == NULL || params == NULL) - return HUBBUB_BADPARM; - - switch (type) { - case HUBBUB_CHARSETCODEC_FILTER_FUNC: - codec->filter = params->filter_func.filter; - codec->filter_pw = params->filter_func.pw; - break; - - case HUBBUB_CHARSETCODEC_ERROR_MODE: - codec->errormode = params->error_mode.mode; - break; - } - - return HUBBUB_OK; -} - -/** - * Encode a chunk of UCS4 data into a codec's charset - * - * \param codec The codec to use - * \param source Pointer to pointer to source data - * \param sourcelen Pointer to length (in bytes) of source data - * \param dest Pointer to pointer to output buffer - * \param destlen Pointer to length (in bytes) of output buffer - * \return HUBBUB_OK on success, appropriate error otherwise. - * - * source, sourcelen, dest and destlen will be updated appropriately on exit - */ -hubbub_error hubbub_charsetcodec_encode(hubbub_charsetcodec *codec, - const uint8_t **source, size_t *sourcelen, - uint8_t **dest, size_t *destlen) -{ - if (codec == NULL || source == NULL || *source == NULL || - sourcelen == NULL || dest == NULL || *dest == NULL || - destlen == NULL) - return HUBBUB_BADPARM; - - return codec->handler.encode(codec, source, sourcelen, dest, destlen); -} - -/** - * Decode a chunk of data in a codec's charset into UCS4 - * - * \param codec The codec to use - * \param source Pointer to pointer to source data - * \param sourcelen Pointer to length (in bytes) of source data - * \param dest Pointer to pointer to output buffer - * \param destlen Pointer to length (in bytes) of output buffer - * \return HUBBUB_OK on success, appropriate error otherwise. - * - * source, sourcelen, dest and destlen will be updated appropriately on exit - * - * Call this with a source length of 0 to flush any buffers. - */ -hubbub_error hubbub_charsetcodec_decode(hubbub_charsetcodec *codec, - const uint8_t **source, size_t *sourcelen, - uint8_t **dest, size_t *destlen) -{ - if (codec == NULL || source == NULL || *source == NULL || - sourcelen == NULL || dest == NULL || *dest == NULL || - destlen == NULL) - return HUBBUB_BADPARM; - - return codec->handler.decode(codec, source, sourcelen, dest, destlen); -} - -/** - * Clear a charset codec's encoding state - * - * \param codec The codec to reset - * \return HUBBUB_OK on success, appropriate error otherwise - */ -hubbub_error hubbub_charsetcodec_reset(hubbub_charsetcodec *codec) -{ - if (codec == NULL) - return HUBBUB_BADPARM; - - /* Reset filter */ - if (codec->filter) - codec->filter(HUBBUB_CHARSETCODEC_NULL, NULL, NULL, NULL); - - return codec->handler.reset(codec); -} - -- cgit v1.2.3