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/parser.c | 70 ++++++++++++++++++------------------------------------------ 1 file changed, 21 insertions(+), 49 deletions(-) (limited to 'src/parser.c') diff --git a/src/parser.c b/src/parser.c index 1ae498a..26b2b1f 100644 --- a/src/parser.c +++ b/src/parser.c @@ -5,9 +5,11 @@ * Copyright 2007-8 John-Mark Bell */ +#include + #include -#include "input/inputstream.h" +#include "charset/detect.h" #include "tokeniser/tokeniser.h" #include "treebuilder/treebuilder.h" @@ -15,7 +17,7 @@ * Hubbub parser object */ struct hubbub_parser { - hubbub_inputstream *stream; /**< Input stream instance */ + parserutils_inputstream *stream; /**< Input stream instance */ hubbub_tokeniser *tok; /**< Tokeniser instance */ hubbub_treebuilder *tb; /**< Treebuilder instance */ @@ -44,7 +46,9 @@ hubbub_parser *hubbub_parser_create(const char *enc, const char *int_enc, if (parser == NULL) return NULL; - parser->stream = hubbub_inputstream_create(enc, int_enc, alloc, pw); + parser->stream = parserutils_inputstream_create(enc, + enc != NULL ? HUBBUB_CHARSET_DICTATED : HUBBUB_CHARSET_UNKNOWN, + hubbub_charset_extract, alloc, pw); if (parser->stream == NULL) { alloc(parser, 0, pw); return NULL; @@ -52,7 +56,7 @@ hubbub_parser *hubbub_parser_create(const char *enc, const char *int_enc, parser->tok = hubbub_tokeniser_create(parser->stream, alloc, pw); if (parser->tok == NULL) { - hubbub_inputstream_destroy(parser->stream); + parserutils_inputstream_destroy(parser->stream); alloc(parser, 0, pw); return NULL; } @@ -60,7 +64,7 @@ hubbub_parser *hubbub_parser_create(const char *enc, const char *int_enc, parser->tb = hubbub_treebuilder_create(parser->tok, alloc, pw); if (parser->tb == NULL) { hubbub_tokeniser_destroy(parser->tok); - hubbub_inputstream_destroy(parser->stream); + parserutils_inputstream_destroy(parser->stream); alloc(parser, 0, pw); return NULL; } @@ -85,7 +89,7 @@ void hubbub_parser_destroy(hubbub_parser *parser) hubbub_tokeniser_destroy(parser->tok); - hubbub_inputstream_destroy(parser->stream); + parserutils_inputstream_destroy(parser->stream); parser->alloc(parser, 0, parser->pw); } @@ -119,19 +123,6 @@ hubbub_error hubbub_parser_setopt(hubbub_parser *parser, HUBBUB_TOKENISER_TOKEN_HANDLER, (hubbub_tokeniser_optparams *) params); break; - case HUBBUB_PARSER_BUFFER_HANDLER: - /* The buffer handler cascades, so if there's a treebuilder, - * simply inform that. Otherwise, tell the tokeniser. */ - if (parser->tb != NULL) { - result = hubbub_treebuilder_setopt(parser->tb, - HUBBUB_TREEBUILDER_BUFFER_HANDLER, - (hubbub_treebuilder_optparams *) params); - } else { - result = hubbub_tokeniser_setopt(parser->tok, - HUBBUB_TOKENISER_BUFFER_HANDLER, - (hubbub_tokeniser_optparams *) params); - } - break; case HUBBUB_PARSER_ERROR_HANDLER: /* The error handler does not cascade, so tell both the * treebuilder (if extant) and the tokeniser. */ @@ -183,14 +174,15 @@ hubbub_error hubbub_parser_setopt(hubbub_parser *parser, hubbub_error hubbub_parser_parse_chunk(hubbub_parser *parser, uint8_t *data, size_t len) { + parserutils_error perror; hubbub_error error; if (parser == NULL || data == NULL) return HUBBUB_BADPARM; - error = hubbub_inputstream_append(parser->stream, data, len); - if (error != HUBBUB_OK) - return error; + perror = parserutils_inputstream_append(parser->stream, data, len); + if (perror != PARSERUTILS_OK) + return !HUBBUB_OK; error = hubbub_tokeniser_run(parser->tok); if (error != HUBBUB_OK) @@ -221,7 +213,7 @@ hubbub_error hubbub_parser_parse_extraneous_chunk(hubbub_parser *parser, if (parser == NULL || data == NULL) return HUBBUB_BADPARM; - error = hubbub_inputstream_insert(parser->stream, data, len); + error = parserutils_inputstream_insert(parser->stream, data, len); if (error != HUBBUB_OK) return error; @@ -240,14 +232,15 @@ hubbub_error hubbub_parser_parse_extraneous_chunk(hubbub_parser *parser, */ hubbub_error hubbub_parser_completed(hubbub_parser *parser) { + parserutils_error perror; hubbub_error error; if (parser == NULL) return HUBBUB_BADPARM; - error = hubbub_inputstream_append(parser->stream, NULL, 0); - if (error != HUBBUB_OK) - return error; + perror = parserutils_inputstream_append(parser->stream, NULL, 0); + if (perror != HUBBUB_OK) + return !HUBBUB_OK; error = hubbub_tokeniser_run(parser->tok); if (error != HUBBUB_OK) @@ -264,32 +257,11 @@ hubbub_error hubbub_parser_completed(hubbub_parser *parser) * \return Pointer to charset name (constant; do not free), or NULL if unknown */ const char *hubbub_parser_read_charset(hubbub_parser *parser, - hubbub_charset_source *source) + uint32_t *source) { if (parser == NULL || source == NULL) return NULL; - return hubbub_inputstream_read_charset(parser->stream, source); + return parserutils_inputstream_read_charset(parser->stream, source); } -/** - * Claim ownership of the document buffer - * - * \param parser Parser 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 parser disclaims - * all ownership rights (and invalidates any internal references it may have - * to the buffer). Therefore, the only parser call which may be made - * after calling this function is to destroy the parser. - */ -hubbub_error hubbub_parser_claim_buffer(hubbub_parser *parser, - uint8_t **buffer, size_t *len) -{ - if (parser == NULL || buffer == NULL || len == NULL) - return HUBBUB_BADPARM; - - return hubbub_inputstream_claim_buffer(parser->stream, buffer, len); -} -- cgit v1.2.3