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

1 files changed, 0 insertions, 380 deletions

diff --git a/src/input/filter.c b/src/input/filter.c
deleted file mode 100644
index 7a97840..0000000
--- a/src/input/filter.c
+++ /dev/null
@@ -1,380 +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 <errno.h>
-#include <stdbool.h>
-#include <stdlib.h>
-#include <string.h>
-
-#include "charset/aliases.h"
-#include "charset/codec.h"
-#include "utils/utils.h"
-
-#include "input/filter.h"
-
-
-/** Input filter */
-struct hubbub_filter {
-	hubbub_charsetcodec *read_codec;	/**< Read codec */
-	hubbub_charsetcodec *write_codec;	/**< Write codec */
-
-	uint32_t filter_output[2];	/**< Filter output buffer */
-	uint32_t last_filter_char;	/**< Last filtered character */
-
-	uint32_t pivot_buf[64];		/**< Conversion pivot buffer */
-
-	bool leftover;			/**< Data remains from last call */
-	uint8_t *pivot_left;		/**< Remaining pivot to write */
-	size_t pivot_len;		/**< Length of pivot remaining */
-
-	struct {
-		uint16_t encoding;	/**< Input encoding */
-	} settings;			/**< Filter settings */
-
-	hubbub_alloc alloc;		/**< Memory (de)allocation function */
-	void *pw;			/**< Client private data */
-};
-
-static hubbub_error hubbub_filter_set_defaults(hubbub_filter *input);
-static hubbub_error hubbub_filter_set_encoding(hubbub_filter *input,
-		const char *enc);
-static hubbub_error read_character_filter(uint32_t c,
-		uint32_t **output, size_t *outputlen, void *pw);
-
-/**
- * Create an input filter
- *
- * \param int_enc  Desired encoding of document
- * \param alloc    Function used to (de)allocate data
- * \param pw       Pointer to client-specific private data (may be NULL)
- * \return Pointer to filter instance, or NULL on failure
- */
-hubbub_filter *hubbub_filter_create(const char *int_enc,
-		hubbub_alloc alloc, void *pw)
-{
-	hubbub_filter *filter;
-
-	if (alloc == NULL)
-		return NULL;
-
-	filter = alloc(NULL, sizeof(*filter), pw);
-	if (!filter)
-		return NULL;
-
-	filter->last_filter_char = 0;
-
-	filter->leftover = false;
-	filter->pivot_left = NULL;
-	filter->pivot_len = 0;
-
-	filter->alloc = alloc;
-	filter->pw = pw;
-
-	if (hubbub_filter_set_defaults(filter) != HUBBUB_OK) {
-		filter->alloc(filter, 0, pw);
-		return NULL;
-	}
-
-	filter->write_codec = hubbub_charsetcodec_create(int_enc, alloc, pw);
-	if (filter->write_codec == NULL) {
-		if (filter->read_codec != NULL)
-			hubbub_charsetcodec_destroy(filter->read_codec);
-		filter->alloc(filter, 0, pw);
-		return NULL;
-	}
-
-	return filter;
-}
-
-/**
- * Destroy an input filter
- *
- * \param input  Pointer to filter instance
- */
-void hubbub_filter_destroy(hubbub_filter *input)
-{
-	if (input == NULL)
-		return;
-
-	if (input->read_codec != NULL)
-		hubbub_charsetcodec_destroy(input->read_codec);
-
-	if (input->write_codec != NULL)
-		hubbub_charsetcodec_destroy(input->write_codec);
-
-	input->alloc(input, 0, input->pw);
-
-	return;
-}
-
-/**
- * Configure an input filter
- *
- * \param input   Pointer to filter instance
- * \param type    Input option type to configure
- * \param params  Option-specific parameters
- * \return HUBBUB_OK on success, appropriate error otherwise
- */
-hubbub_error hubbub_filter_setopt(hubbub_filter *input,
-		hubbub_filter_opttype type,
-		hubbub_filter_optparams *params)
-{
-	hubbub_error error = HUBBUB_OK;
-
-	if (input == NULL || params == NULL)
-		return HUBBUB_BADPARM;
-
-	switch (type) {
-	case HUBBUB_FILTER_SET_ENCODING:
-		error = hubbub_filter_set_encoding(input,
-				params->encoding.name);
-		break;
-	}
-
-	return error;
-}
-
-/**
- * Process a chunk of data
- *
- * \param input   Pointer to filter instance
- * \param data    Pointer to pointer to input buffer
- * \param len     Pointer to length of input buffer
- * \param output  Pointer to pointer to output buffer
- * \param outlen  Pointer to length of output buffer
- * \return HUBBUB_OK on success, appropriate error otherwise
- *
- * Call this with an input buffer length of 0 to flush any buffers.
- */
-hubbub_error hubbub_filter_process_chunk(hubbub_filter *input,
-		const uint8_t **data, size_t *len,
-		uint8_t **output, size_t *outlen)
-{
-	hubbub_error read_error, write_error;
-
-	if (input == NULL || data == NULL || *data == NULL || len == NULL ||
-			output == NULL || *output == NULL || outlen == NULL)
-		return HUBBUB_BADPARM;
-
-	if (input->leftover) {
-		/* Some data left to be written from last call */
-
-		/* Attempt to flush the remaining data. */
-		write_error = hubbub_charsetcodec_encode(input->write_codec,
-				(const uint8_t **) &input->pivot_left,
-				&input->pivot_len,
-				output, outlen);
-
-		if (write_error != HUBBUB_OK) {
-			return write_error;
-		}
-
-		/* And clear leftover */
-		input->pivot_left = NULL;
-		input->pivot_len = 0;
-		input->leftover = false;
-	}
-
-	while (*len > 0) {
-		size_t pivot_len = sizeof(input->pivot_buf);
-		uint8_t *pivot = (uint8_t *) input->pivot_buf;
-
-		read_error = hubbub_charsetcodec_decode(input->read_codec,
-				data, len,
-				(uint8_t **) &pivot, &pivot_len);
-
-		pivot = (uint8_t *) input->pivot_buf;
-		pivot_len = sizeof(input->pivot_buf) - pivot_len;
-
-		if (pivot_len > 0) {
-			write_error = hubbub_charsetcodec_encode(
-					input->write_codec,
-					(const uint8_t **) &pivot,
-					&pivot_len,
-					output, outlen);
-
-			if (write_error != HUBBUB_OK) {
-				input->leftover = true;
-				input->pivot_left = pivot;
-				input->pivot_len = pivot_len;
-
-				return write_error;
-			}
-		}
-
-		if (read_error != HUBBUB_OK && read_error != HUBBUB_NOMEM)
-			return read_error;
-	}
-
-	return HUBBUB_OK;
-}
-
-/**
- * Reset an input filter's state
- *
- * \param input  The input filter to reset
- * \param HUBBUB_OK on success, appropriate error otherwise
- */
-hubbub_error hubbub_filter_reset(hubbub_filter *input)
-{
-	hubbub_error error;
-
-	if (input == NULL)
-		return HUBBUB_BADPARM;
-
-	/* Clear pivot buffer leftovers */
-	input->pivot_left = NULL;
-	input->pivot_len = 0;
-	input->leftover = false;
-
-	/* Reset read codec */
-	error = hubbub_charsetcodec_reset(input->read_codec);
-	if (error != HUBBUB_OK)
-		return error;
-
-	/* Reset write codec */
-	error = hubbub_charsetcodec_reset(input->write_codec);
-	if (error != HUBBUB_OK)
-		return error;
-
-	return HUBBUB_OK;
-}
-
-/**
- * Set an input filter's default settings
- *
- * \param input  Input filter to configure
- * \return HUBBUB_OK on success, appropriate error otherwise
- */
-hubbub_error hubbub_filter_set_defaults(hubbub_filter *input)
-{
-	hubbub_error error;
-
-	if (input == NULL)
-		return HUBBUB_BADPARM;
-
-	input->read_codec = NULL;
-	input->write_codec = NULL;
-	input->settings.encoding = 0;
-	error = hubbub_filter_set_encoding(input, "ISO-8859-1");
-	if (error != HUBBUB_OK)
-		return error;
-
-	return HUBBUB_OK;
-}
-
-/**
- * Set an input filter's encoding
- *
- * \param input  Input filter to configure
- * \param enc    Encoding name
- * \return HUBBUB_OK on success, appropriate error otherwise
- */
-hubbub_error hubbub_filter_set_encoding(hubbub_filter *input,
-		const char *enc)
-{
-	const char *old_enc;
-	uint16_t mibenum;
-	hubbub_error error;
-	hubbub_charsetcodec_optparams params;
-
-	if (input == NULL || enc == NULL)
-		return HUBBUB_BADPARM;
-
-	mibenum = hubbub_mibenum_from_name(enc, strlen(enc));
-	if (mibenum == 0)
-		return HUBBUB_INVALID;
-
-	/* Exit early if we're already using this encoding */
-	if (input->settings.encoding == mibenum)
-		return HUBBUB_OK;
-
-	old_enc = hubbub_mibenum_to_name(input->settings.encoding);
-	if (old_enc == NULL)
-		old_enc = "ISO-8859-1";
-
-	if (input->read_codec != NULL)
-		hubbub_charsetcodec_destroy(input->read_codec);
-
-	input->read_codec = hubbub_charsetcodec_create(enc, input->alloc,
-			input->pw);
-	if (input->read_codec == NULL)
-		return HUBBUB_NOMEM;
-
-	/* Register filter function */
-	params.filter_func.filter = read_character_filter;
-	params.filter_func.pw = (void *) input;
-	error = hubbub_charsetcodec_setopt(input->read_codec,
-			HUBBUB_CHARSETCODEC_FILTER_FUNC,
-			(hubbub_charsetcodec_optparams *) &params);
-	if (error != HUBBUB_OK)
-		return error;
-
-	input->settings.encoding = mibenum;
-
-	return HUBBUB_OK;
-}
-
-/**
- * Character filter function for read characters
- *
- * \param c          The read character (UCS4 - host byte order)
- * \param output     Pointer to pointer to output buffer (filled on exit)
- * \param outputlen  Pointer to output buffer length (filled on exit)
- * \param pw         Pointer to client-specific private data.
- * \return HUBBUB_OK on success, appropriate error otherwise
- */
-hubbub_error read_character_filter(uint32_t c, uint32_t **output,
-		size_t *outputlen, void *pw)
-{
-	hubbub_filter *input = (hubbub_filter *) pw;
-	size_t len;
-
-	if (output == NULL || outputlen == NULL || pw == NULL)
-		return HUBBUB_BADPARM;
-
-	/* Line ending normalisation:
-	 *   CRLF -> LF  (trap CR and let LF through unmodified)
-	 *   CR   -> LF  (trap CR and convert to LF if not CRLF)
-	 *   LF   -> LF  (leave LF alone)
-	 */
-
-#define NUL (0x00000000)
-#define CR  (0x0000000D)
-#define LF  (0x0000000A)
-#define REP (0x0000FFFD)
-
-	/* Replace NUL (U+0000) characters in input with U+FFFD */
-	if (c == NUL)
-		c = REP;
-
-	if (c == CR) {
-		/* Convert CRs to LFs straight away */
-		input->filter_output[0] = LF;
-		len = 1;
-	} else if (input->last_filter_char == CR && c == LF) {
-		/* Trap this LF */
-		len = 0;
-	} else {
-		/* Let character through unchanged */
-		input->filter_output[0] = c;
-		len = 1;
-	}
-
-
-#undef NUL
-#undef CR
-#undef LF
-#undef REP
-
-	input->last_filter_char = c;
-
-	*output = input->filter_output;
-	*outputlen = len;
-
-	return HUBBUB_OK;
-}