summaryrefslogtreecommitdiff
path: root/src/treebuilder/treebuilder.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/treebuilder/treebuilder.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/treebuilder/treebuilder.c')
-rw-r--r--src/treebuilder/treebuilder.c115
1 files changed, 32 insertions, 83 deletions
diff --git a/src/treebuilder/treebuilder.c b/src/treebuilder/treebuilder.c
index f739113..c6d8f69 100644
--- a/src/treebuilder/treebuilder.c
+++ b/src/treebuilder/treebuilder.c
@@ -76,9 +76,6 @@ static const struct {
};
-static void hubbub_treebuilder_buffer_handler(const uint8_t *data,
- size_t len, void *pw);
-
/**
* Create a hubbub treebuilder
@@ -103,9 +100,6 @@ hubbub_treebuilder *hubbub_treebuilder_create(hubbub_tokeniser *tokeniser,
tb->tokeniser = tokeniser;
- tb->input_buffer = NULL;
- tb->input_buffer_len = 0;
-
tb->tree_handler = NULL;
memset(&tb->context, 0, sizeof(hubbub_treebuilder_context));
@@ -124,13 +118,8 @@ hubbub_treebuilder *hubbub_treebuilder_create(hubbub_tokeniser *tokeniser,
assert(HTML != 0);
tb->context.element_stack[0].type = 0;
- tb->context.collect.string.type = HUBBUB_STRING_OFF;
-
tb->context.strip_leading_lr = false;
- tb->buffer_handler = NULL;
- tb->buffer_pw = NULL;
-
tb->error_handler = NULL;
tb->error_pw = NULL;
@@ -147,17 +136,7 @@ hubbub_treebuilder *hubbub_treebuilder_create(hubbub_tokeniser *tokeniser,
return NULL;
}
- tokparams.buffer_handler.handler = hubbub_treebuilder_buffer_handler;
- tokparams.buffer_handler.pw = tb;
-
- if (hubbub_tokeniser_setopt(tokeniser, HUBBUB_TOKENISER_BUFFER_HANDLER,
- &tokparams) != HUBBUB_OK) {
- alloc(tb->context.element_stack, 0, pw);
- alloc(tb, 0, pw);
- return NULL;
- }
-
- return tb;
+ return tb;
}
/**
@@ -173,12 +152,6 @@ void hubbub_treebuilder_destroy(hubbub_treebuilder *treebuilder)
if (treebuilder == NULL)
return;
- tokparams.buffer_handler.handler = treebuilder->buffer_handler;
- tokparams.buffer_handler.pw = treebuilder->buffer_pw;
-
- hubbub_tokeniser_setopt(treebuilder->tokeniser,
- HUBBUB_TOKENISER_BUFFER_HANDLER, &tokparams);
-
tokparams.token_handler.handler = NULL;
tokparams.token_handler.pw = NULL;
@@ -253,13 +226,6 @@ hubbub_error hubbub_treebuilder_setopt(hubbub_treebuilder *treebuilder,
return HUBBUB_BADPARM;
switch (type) {
- case HUBBUB_TREEBUILDER_BUFFER_HANDLER:
- treebuilder->buffer_handler = params->buffer_handler.handler;
- treebuilder->buffer_pw = params->buffer_handler.pw;
- treebuilder->buffer_handler(treebuilder->input_buffer,
- treebuilder->input_buffer_len,
- treebuilder->buffer_pw);
- break;
case HUBBUB_TREEBUILDER_ERROR_HANDLER:
treebuilder->error_handler = params->error_handler.handler;
treebuilder->error_pw = params->error_handler.pw;
@@ -276,29 +242,6 @@ hubbub_error hubbub_treebuilder_setopt(hubbub_treebuilder *treebuilder,
}
/**
- * Handle tokeniser buffer moving
- *
- * \param data New location of buffer
- * \param len Length of buffer in bytes
- * \param pw Pointer to treebuilder instance
- */
-void hubbub_treebuilder_buffer_handler(const uint8_t *data,
- size_t len, void *pw)
-{
- hubbub_treebuilder *treebuilder = (hubbub_treebuilder *) pw;
-
- treebuilder->input_buffer = data;
- treebuilder->input_buffer_len = len;
-
- /* Inform client buffer handler, too (if there is one) */
- if (treebuilder->buffer_handler != NULL) {
- treebuilder->buffer_handler(treebuilder->input_buffer,
- treebuilder->input_buffer_len,
- treebuilder->buffer_pw);
- }
-}
-
-/**
* Handle tokeniser emitting a token
*
* \param token The emitted token
@@ -418,8 +361,7 @@ void hubbub_treebuilder_token_handler(const hubbub_token *token,
bool process_characters_expect_whitespace(hubbub_treebuilder *treebuilder,
const hubbub_token *token, bool insert_into_current_node)
{
- const uint8_t *data = treebuilder->input_buffer +
- token->data.character.data.off;
+ const uint8_t *data = token->data.character.ptr;
size_t len = token->data.character.len;
size_t c;
@@ -434,8 +376,7 @@ bool process_characters_expect_whitespace(hubbub_treebuilder *treebuilder,
if (c > 0 && insert_into_current_node) {
hubbub_string temp;
- temp.type = HUBBUB_STRING_OFF;
- temp.data.off = token->data.character.data.off;
+ temp.ptr = data;
temp.len = c;
append_text(treebuilder, &temp);
@@ -444,7 +385,7 @@ bool process_characters_expect_whitespace(hubbub_treebuilder *treebuilder,
/* Non-whitespace characters in token, so reprocess */
if (c != len) {
/* Update token data to strip leading whitespace */
- ((hubbub_token *) token)->data.character.data.off += c;
+ ((hubbub_token *) token)->data.character.ptr += c;
((hubbub_token *) token)->data.character.len -= c;
return true;
@@ -566,7 +507,7 @@ void parse_generic_rcdata(hubbub_treebuilder *treebuilder,
treebuilder->context.collect.mode = treebuilder->context.mode;
treebuilder->context.collect.type = type;
treebuilder->context.collect.node = appended;
- treebuilder->context.collect.string.data.off = 0;
+ treebuilder->context.collect.string.ptr = NULL;
treebuilder->context.collect.string.len = 0;
treebuilder->tree_handler->unref_node(
@@ -651,6 +592,7 @@ void reconstruct_active_formatting_list(hubbub_treebuilder *treebuilder)
while (entry != NULL) {
int success;
void *clone, *appended;
+ hubbub_ns prev_ns;
element_type prev_type;
void *prev_node;
uint32_t prev_stack_index;
@@ -719,9 +661,9 @@ void reconstruct_active_formatting_list(hubbub_treebuilder *treebuilder)
}
if (!formatting_list_replace(treebuilder, entry,
- entry->details.type, appended,
- treebuilder->context.current_node,
- &prev_type, &prev_node,
+ entry->details.ns, entry->details.type,
+ appended, treebuilder->context.current_node,
+ &prev_ns, &prev_type, &prev_node,
&prev_stack_index)) {
/** \todo handle errors */
treebuilder->tree_handler->unref_node(
@@ -748,6 +690,7 @@ void clear_active_formatting_list_to_marker(hubbub_treebuilder *treebuilder)
bool done = false;
while ((entry = treebuilder->context.formatting_list_end) != NULL) {
+ hubbub_ns ns;
element_type type;
void *node;
uint32_t stack_index;
@@ -756,7 +699,7 @@ void clear_active_formatting_list_to_marker(hubbub_treebuilder *treebuilder)
done = true;
if (!formatting_list_remove(treebuilder, entry,
- &type, &node, &stack_index)) {
+ &ns, &type, &node, &stack_index)) {
/** \todo handle errors */
}
@@ -1009,18 +952,9 @@ void append_text(hubbub_treebuilder *treebuilder,
element_type element_type_from_name(hubbub_treebuilder *treebuilder,
const hubbub_string *tag_name)
{
- const uint8_t *name = NULL;
+ const uint8_t *name = tag_name->ptr;
size_t len = tag_name->len;
- switch (tag_name->type) {
- case HUBBUB_STRING_OFF:
- name = treebuilder->input_buffer + tag_name->data.off;
- break;
- case HUBBUB_STRING_PTR:
- name = tag_name->data.ptr;
- break;
- }
-
/** \todo UTF-16 support */
/** \todo optimise this */
@@ -1249,13 +1183,15 @@ element_type prev_node(hubbub_treebuilder *treebuilder)
* Append an element to the end of the list of active formatting elements
*
* \param treebuilder Treebuilder instance containing list
+ * \param ns Namespace of node being inserted
* \param type Type of node being inserted
* \param node Node being inserted
* \param stack_index Index into stack of open elements
* \return True on success, false on memory exhaustion
*/
bool formatting_list_append(hubbub_treebuilder *treebuilder,
- element_type type, void *node, uint32_t stack_index)
+ hubbub_ns ns, element_type type, void *node,
+ uint32_t stack_index)
{
formatting_list_entry *entry;
@@ -1264,6 +1200,7 @@ bool formatting_list_append(hubbub_treebuilder *treebuilder,
if (entry == NULL)
return false;
+ entry->details.ns = ns;
entry->details.type = type;
entry->details.node = node;
entry->stack_index = stack_index;
@@ -1287,6 +1224,7 @@ bool formatting_list_append(hubbub_treebuilder *treebuilder,
* \param treebuilder Treebuilder instance containing list
* \param prev Previous entry
* \param next Next entry
+ * \param ns Namespace of node being inserted
* \param type Type of node being inserted
* \param node Node being inserted
* \param stack_index Index into stack of open elements
@@ -1294,7 +1232,8 @@ bool formatting_list_append(hubbub_treebuilder *treebuilder,
*/
bool formatting_list_insert(hubbub_treebuilder *treebuilder,
formatting_list_entry *prev, formatting_list_entry *next,
- element_type type, void *node, uint32_t stack_index)
+ hubbub_ns ns, element_type type, void *node,
+ uint32_t stack_index)
{
formatting_list_entry *entry;
@@ -1311,6 +1250,7 @@ bool formatting_list_insert(hubbub_treebuilder *treebuilder,
if (entry == NULL)
return false;
+ entry->details.ns = ns;
entry->details.type = type;
entry->details.node = node;
entry->stack_index = stack_index;
@@ -1337,6 +1277,7 @@ bool formatting_list_insert(hubbub_treebuilder *treebuilder,
*
* \param treebuilder Treebuilder instance containing list
* \param entry The item to remove
+ * \param ns Pointer to location to receive namespace of node
* \param type Pointer to location to receive type of node
* \param node Pointer to location to receive node
* \param stack_index Pointer to location to receive stack index
@@ -1344,8 +1285,10 @@ bool formatting_list_insert(hubbub_treebuilder *treebuilder,
*/
bool formatting_list_remove(hubbub_treebuilder *treebuilder,
formatting_list_entry *entry,
- element_type *type, void **node, uint32_t *stack_index)
+ hubbub_ns *ns, element_type *type, void **node,
+ uint32_t *stack_index)
{
+ *ns = entry->details.ns;
*type = entry->details.type;
*node = entry->details.node;
*stack_index = entry->stack_index;
@@ -1370,9 +1313,11 @@ bool formatting_list_remove(hubbub_treebuilder *treebuilder,
*
* \param treebuilder Treebuilder instance containing list
* \param entry The item to replace
+ * \param ns Replacement node namespace
* \param type Replacement node type
* \param node Replacement node
* \param stack_index Replacement stack index
+ * \param ons Pointer to location to receive old namespace
* \param otype Pointer to location to receive old type
* \param onode Pointer to location to receive old node
* \param ostack_index Pointer to location to receive old stack index
@@ -1380,15 +1325,19 @@ bool formatting_list_remove(hubbub_treebuilder *treebuilder,
*/
bool formatting_list_replace(hubbub_treebuilder *treebuilder,
formatting_list_entry *entry,
- element_type type, void *node, uint32_t stack_index,
- element_type *otype, void **onode, uint32_t *ostack_index)
+ hubbub_ns ns, element_type type, void *node,
+ uint32_t stack_index,
+ hubbub_ns *ons, element_type *otype, void **onode,
+ uint32_t *ostack_index)
{
UNUSED(treebuilder);
+ *ons = entry->details.ns;
*otype = entry->details.type;
*onode = entry->details.node;
*ostack_index = entry->stack_index;
+ entry->details.ns = ns;
entry->details.type = type;
entry->details.node = node;
entry->stack_index = stack_index;