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 --- test/tokeniser3.c | 108 ++++++++++++++++++++++++++---------------------------- 1 file changed, 52 insertions(+), 56 deletions(-) (limited to 'test/tokeniser3.c') diff --git a/test/tokeniser3.c b/test/tokeniser3.c index 76b1d07..05f57b4 100644 --- a/test/tokeniser3.c +++ b/test/tokeniser3.c @@ -4,18 +4,17 @@ #include +#include + #include #include "utils/utils.h" -#include "input/inputstream.h" #include "tokeniser/tokeniser.h" #include "testutils.h" typedef struct context { - const uint8_t *pbuffer; - const uint8_t *input; size_t input_len; @@ -29,7 +28,6 @@ typedef struct context { } context; static void run_test(context *ctx); -static void buffer_handler(const uint8_t *buffer, size_t len, void *pw); static void token_handler(const hubbub_token *token, void *pw); static void *myrealloc(void *ptr, size_t len, void *pw) @@ -74,6 +72,7 @@ int main(int argc, char **argv) ctx.last_start_tag = NULL; ctx.content_model = NULL; + ctx.process_cdata = false; /* Extract settings */ for (entry = json_object_get_object(test)->head; entry; @@ -117,7 +116,7 @@ int main(int argc, char **argv) void run_test(context *ctx) { - hubbub_inputstream *stream; + parserutils_inputstream *stream; hubbub_tokeniser *tok; hubbub_tokeniser_optparams params; int i, max_i; @@ -137,7 +136,7 @@ void run_test(context *ctx) ctx->output_index = 0; ctx->char_off = 0; - stream = hubbub_inputstream_create("UTF-8", "UTF-8", + stream = parserutils_inputstream_create("UTF-8", 0, NULL, myrealloc, NULL); assert(stream != NULL); @@ -151,7 +150,7 @@ void run_test(context *ctx) snprintf((char *) buf, sizeof buf, "<%s>", ctx->last_start_tag); - assert(hubbub_inputstream_append(stream, + assert(parserutils_inputstream_append(stream, buf, strlen(ctx->last_start_tag) + 2) == HUBBUB_OK); @@ -165,12 +164,6 @@ void run_test(context *ctx) ¶ms) == HUBBUB_OK); } - params.buffer_handler.handler = buffer_handler; - params.buffer_handler.pw = ctx; - assert(hubbub_tokeniser_setopt(tok, - HUBBUB_TOKENISER_BUFFER_HANDLER, - ¶ms) == HUBBUB_OK); - params.token_handler.handler = token_handler; params.token_handler.pw = ctx; assert(hubbub_tokeniser_setopt(tok, @@ -208,33 +201,24 @@ void run_test(context *ctx) (int) ctx->input_len); for (j = 0; j < ctx->input_len; j++) { - assert(hubbub_inputstream_append(stream, + assert(parserutils_inputstream_append(stream, ctx->input + j, 1) == HUBBUB_OK); assert(hubbub_tokeniser_run(tok) == HUBBUB_OK); } - assert(hubbub_inputstream_append(stream, NULL, 0) == + assert(parserutils_inputstream_append(stream, NULL, 0) == HUBBUB_OK); assert(hubbub_tokeniser_run(tok) == HUBBUB_OK); hubbub_tokeniser_destroy(tok); - hubbub_inputstream_destroy(stream); + parserutils_inputstream_destroy(stream); } } -void buffer_handler(const uint8_t *buffer, size_t len, void *pw) -{ - context *ctx = (context *) pw; - - UNUSED(len); - - ctx->pbuffer = buffer; -} - void token_handler(const hubbub_token *token, void *pw) { static const char *token_names[] = { @@ -301,9 +285,9 @@ void token_handler(const hubbub_token *token, void *pw) array_list_get_idx(items, 3)); bool expquirks = !json_object_get_boolean( array_list_get_idx(items, 4)); - char *gotname = (char *) (ctx->pbuffer + - token->data.doctype.name.data.off); - char *gotpub, *gotsys; + const char *gotname = (const char *) + token->data.doctype.name.ptr; + const char *gotpub, *gotsys; printf("'%.*s' %sids:\n", (int) token->data.doctype.name.len, @@ -315,34 +299,38 @@ void token_handler(const hubbub_token *token, void *pw) gotpub = NULL; printf("\tpublic: missing\n"); } else { - gotpub = (char *) (ctx->pbuffer + - token->data.doctype.public_id.data.off); - printf("\tpublic: '%.*s'\n", + gotpub = (const char *) + token->data.doctype.public_id.ptr; + printf("\tpublic: '%.*s' (%d)\n", (int) token->data.doctype.public_id.len, - gotpub); + gotpub, + (int) token->data.doctype.public_id.len); } if (token->data.doctype.system_missing) { gotsys = NULL; printf("\tsystem: missing\n"); } else { - gotsys = (char *) (ctx->pbuffer + - token->data.doctype.system_id.data.off); - printf("\tsystem: '%.*s'\n", + gotsys = (const char *) + token->data.doctype.system_id.ptr; + printf("\tsystem: '%.*s' (%d)\n", (int) token->data.doctype.system_id.len, - gotsys); + gotsys, + (int) token->data.doctype.system_id.len); } assert(token->data.doctype.name.len == strlen(expname)); assert(strncmp(gotname, expname, strlen(expname)) == 0); - assert((exppub == NULL) == (gotpub == NULL)); + assert((exppub == NULL) == + (token->data.doctype.public_missing == true)); if (exppub) { assert(token->data.doctype.public_id.len == strlen(exppub)); assert(strncmp(gotpub, exppub, strlen(exppub)) == 0); } - assert((expsys == NULL) == (gotsys == NULL)); + assert((expsys == NULL) == + (token->data.doctype.system_missing == true)); if (gotsys) { assert(token->data.doctype.system_id.len == strlen(expsys)); assert(strncmp(gotsys, expsys, strlen(expsys)) == 0); @@ -360,16 +348,22 @@ void token_handler(const hubbub_token *token, void *pw) bool self_closing = json_object_get_boolean( array_list_get_idx(items, 3)); - char *tagname = (char *) (ctx->pbuffer + - token->data.tag.name.data.off); + const char *tagname = (const char *) + token->data.tag.name.ptr; - printf("'%.*s' %s%s\n", + printf("expected: '%s' %s\n", + expname, + (self_closing) ? "(self-closing) " : ""); + + printf(" got: '%.*s' %s\n", (int) token->data.tag.name.len, tagname, (token->data.tag.self_closing) ? - "(self-closing) " : "", - (token->data.tag.n_attributes > 0) ? - "attributes:" : ""); + "(self-closing) " : ""); + + if (token->data.tag.n_attributes > 0) { + printf("attributes:\n"); + } assert(token->data.tag.name.len == strlen(expname)); assert(strncmp(tagname, expname, strlen(expname)) == 0); @@ -383,12 +377,12 @@ void token_handler(const hubbub_token *token, void *pw) char *expname = (char *) expattrs->k; char *expval = json_object_get_string( (struct json_object *) expattrs->v); - char *gotname = (char *) (ctx->pbuffer + - token->data.tag.attributes[i].name.data.off); + const char *gotname = (const char *) + token->data.tag.attributes[i].name.ptr; size_t namelen = token->data.tag.attributes[i].name.len; - char *gotval = (char *) (ctx->pbuffer + - token->data.tag.attributes[i].value.data.off); + const char *gotval = (const char *) + token->data.tag.attributes[i].value.ptr; size_t vallen = token->data.tag.attributes[i].value.len; @@ -412,8 +406,8 @@ void token_handler(const hubbub_token *token, void *pw) { char *expname = json_object_get_string( array_list_get_idx(items, 1)); - char *tagname = (char *) (ctx->pbuffer + - token->data.tag.name.data.off); + const char *tagname = (const char *) + token->data.tag.name.ptr; printf("'%.*s' %s\n", (int) token->data.tag.name.len, @@ -429,10 +423,12 @@ void token_handler(const hubbub_token *token, void *pw) { char *expstr = json_object_get_string( array_list_get_idx(items, 1)); - char *gotstr = (char *) (ctx->pbuffer + - token->data.comment.data.off); + const char *gotstr = (const char *) + token->data.comment.ptr; - printf("'%.*s'\n", (int) token->data.comment.len, gotstr); + printf("expected: '%s'\n", expstr); + printf(" got: '%.*s'\n", + (int) token->data.comment.len, gotstr); assert(token->data.comment.len == strlen(expstr)); assert(strncmp(gotstr, expstr, strlen(expstr)) == 0); @@ -443,8 +439,8 @@ void token_handler(const hubbub_token *token, void *pw) int expstrlen; char *expstr = json_object_get_string_len( array_list_get_idx(items, 1), &expstrlen); - char *gotstr = (char *) (ctx->pbuffer + - token->data.character.data.off); + const char *gotstr = (const char *) + token->data.character.ptr; size_t len = min(token->data.character.len, expstrlen - ctx->char_off); @@ -462,7 +458,7 @@ void token_handler(const hubbub_token *token, void *pw) hubbub_token t; t.type = HUBBUB_TOKEN_CHARACTER; - t.data.character.data.off += len; + t.data.character.ptr += len; t.data.character.len -= len; ctx->char_off = 0; -- cgit v1.2.3