Gitweb links: ...log http://git.netsurf-browser.org/libhubbub.git/shortlog/cc2330f8d52b921836f... ...commit http://git.netsurf-browser.org/libhubbub.git/commit/cc2330f8d52b921836f9d... ...tree http://git.netsurf-browser.org/libhubbub.git/tree/cc2330f8d52b921836f9d30... The branch, rupindersingh/libhubbub has been updated discards e61c714744a2346dd8399125c02a7983878f7bdd (commit) via cc2330f8d52b921836f9d30147f9280b3ecf1733 (commit) This update added new revisions after undoing existing revisions. That is to say, the old revision is not a strict subset of the new revision. This situation occurs when you --force push a change and generate a repository containing something like this: * -- * -- B -- O -- O -- O (e61c714744a2346dd8399125c02a7983878f7bdd) \ N -- N -- N (cc2330f8d52b921836f9d30147f9280b3ecf1733) When this happens we assume that you've already had alert emails for all of the O revisions, and so we here report only the revisions in the N branch from the common base, B. Those revisions listed above that are new to this repository have not appeared on any other notification email; so we list those revisions in full, below. - Log ----------------------------------------------------------------- commitdiff http://git.netsurf-browser.org/libhubbub.git/commit/?id=cc2330f8d52b92183... commit cc2330f8d52b921836f9d30147f9280b3ecf1733 Author: Rupinder Singh Khokhar <rsk1coder99(a)gmail.com&gt; Commit: Rupinder Singh Khokhar <rsk1coder99(a)gmail.com&gt; Adding PLAINTEXT State & fixing the tester at places diff --git a/include/hubbub/types.h b/include/hubbub/types.h index e5c208b..6e2b1a9 100644 --- a/include/hubbub/types.h +++ b/include/hubbub/types.h @@ -33,7 +33,8 @@ typedef enum hubbub_content_model { HUBBUB_CONTENT_MODEL_PCDATA, HUBBUB_CONTENT_MODEL_RCDATA, HUBBUB_CONTENT_MODEL_CDATA, - HUBBUB_CONTENT_MODEL_PLAINTEXT + HUBBUB_CONTENT_MODEL_PLAINTEXT, + HUBBUB_CONTENT_MODEL_RAWTEXT } hubbub_content_model; /** diff --git a/src/tokeniser/tokeniser.c b/src/tokeniser/tokeniser.c index 22fa862..9ec05ce 100644 --- a/src/tokeniser/tokeniser.c +++ b/src/tokeniser/tokeniser.c @@ -759,12 +759,16 @@ hubbub_error hubbub_tokeniser_handle_data(hubbub_tokeniser *tokeniser) emit_current_chars(tokeniser); } - /* Emit a null character */ - emit_character_token(tokeniser, &u_null_str); + /* Emit a null or a replacement character */ + if(tokeniser->content_model == HUBBUB_CONTENT_MODEL_PLAINTEXT) { + emit_character_token(tokeniser, &u_fffd_str); + } else { + emit_character_token(tokeniser, &u_null_str); + } /* Advance past NUL */ parserutils_inputstream_advance(tokeniser->input, 1); - } else if (c == '\r') { + } else if (c == '\r' && tokeniser->content_model != HUBBUB_CONTENT_MODEL_PLAINTEXT) { error = parserutils_inputstream_peek( tokeniser->input, tokeniser->context.pending + len, diff --git a/test/tokeniser2.c b/test/tokeniser2.c index 07f355a..a0264c9 100644 --- a/test/tokeniser2.c +++ b/test/tokeniser2.c @@ -86,7 +86,7 @@ int main(int argc, char **argv) } else if (strcmp(key, "lastStartTag") == 0) { ctx.last_start_tag = (const char *) json_object_get_string(val); - } else if (strcmp(key, "contentModelFlags") == 0) { + } else if (strcmp(key, "initialStates") == 0) { ctx.content_model = json_object_get_array(val); } else if (strcmp(key, "processCDATA") == 0) { @@ -169,15 +169,18 @@ void run_test(context *ctx) (struct json_object *) array_list_get_idx(ctx->content_model, i)); - if (strcmp(cm, "PCDATA") == 0) { + if (strcmp(cm, "PCDATA state") == 0) { params.content_model.model = HUBBUB_CONTENT_MODEL_PCDATA; - } else if (strcmp(cm, "RCDATA") == 0) { + } else if (strcmp(cm, "RCDATA state") == 0) { params.content_model.model = HUBBUB_CONTENT_MODEL_RCDATA; - } else if (strcmp(cm, "CDATA") == 0) { + } else if (strcmp(cm, "CDATA state") == 0) { params.content_model.model = HUBBUB_CONTENT_MODEL_CDATA; + } else if (strcmp(cm, "RAWTEXT state") == 0) { + params.content_model.model = + HUBBUB_CONTENT_MODEL_RAWTEXT; } else { params.content_model.model = HUBBUB_CONTENT_MODEL_PLAINTEXT; diff --git a/test/tokeniser3.c b/test/tokeniser3.c index e68a230..86f079b 100644 --- a/test/tokeniser3.c +++ b/test/tokeniser3.c @@ -85,7 +85,7 @@ int main(int argc, char **argv) } else if (strcmp(key, "lastStartTag") == 0) { ctx.last_start_tag = (const char *) json_object_get_string(val); - } else if (strcmp(key, "contentModelFlags") == 0) { + } else if (strcmp(key, "initialStates") == 0) { ctx.content_model = json_object_get_array(val); } else if (strcmp(key, "processCDATA") == 0) { @@ -167,15 +167,18 @@ void run_test(context *ctx) (struct json_object *) array_list_get_idx(ctx->content_model, i)); - if (strcmp(cm, "PCDATA") == 0) { + if (strcmp(cm, "PCDATA state") == 0) { params.content_model.model = HUBBUB_CONTENT_MODEL_PCDATA; - } else if (strcmp(cm, "RCDATA") == 0) { + } else if (strcmp(cm, "RCDATA state") == 0) { params.content_model.model = HUBBUB_CONTENT_MODEL_RCDATA; - } else if (strcmp(cm, "CDATA") == 0) { + } else if (strcmp(cm, "CDATA state") == 0) { params.content_model.model = HUBBUB_CONTENT_MODEL_CDATA; + } else if (strcmp(cm, "RAWTEXT state") == 0) { + params.content_model.model = + HUBBUB_CONTENT_MODEL_RAWTEXT; } else { params.content_model.model = HUBBUB_CONTENT_MODEL_PLAINTEXT; ----------------------------------------------------------------------- Summary of changes: src/tokeniser/tokeniser.c | 10 +++++++--- test/tokeniser2.c | 11 +++++++---- test/tokeniser3.c | 11 +++++++---- 3 files changed, 21 insertions(+), 11 deletions(-) diff --git a/src/tokeniser/tokeniser.c b/src/tokeniser/tokeniser.c index 22fa862..9ec05ce 100644 --- a/src/tokeniser/tokeniser.c +++ b/src/tokeniser/tokeniser.c @@ -759,12 +759,16 @@ hubbub_error hubbub_tokeniser_handle_data(hubbub_tokeniser *tokeniser) emit_current_chars(tokeniser); } - /* Emit a null character */ - emit_character_token(tokeniser, &u_null_str); + /* Emit a null or a replacement character */ + if(tokeniser->content_model == HUBBUB_CONTENT_MODEL_PLAINTEXT) { + emit_character_token(tokeniser, &u_fffd_str); + } else { + emit_character_token(tokeniser, &u_null_str); + } /* Advance past NUL */ parserutils_inputstream_advance(tokeniser->input, 1); - } else if (c == '\r') { + } else if (c == '\r' && tokeniser->content_model != HUBBUB_CONTENT_MODEL_PLAINTEXT) { error = parserutils_inputstream_peek( tokeniser->input, tokeniser->context.pending + len, diff --git a/test/tokeniser2.c b/test/tokeniser2.c index 07f355a..a0264c9 100644 --- a/test/tokeniser2.c +++ b/test/tokeniser2.c @@ -86,7 +86,7 @@ int main(int argc, char **argv) } else if (strcmp(key, "lastStartTag") == 0) { ctx.last_start_tag = (const char *) json_object_get_string(val); - } else if (strcmp(key, "contentModelFlags") == 0) { + } else if (strcmp(key, "initialStates") == 0) { ctx.content_model = json_object_get_array(val); } else if (strcmp(key, "processCDATA") == 0) { @@ -169,15 +169,18 @@ void run_test(context *ctx) (struct json_object *) array_list_get_idx(ctx->content_model, i)); - if (strcmp(cm, "PCDATA") == 0) { + if (strcmp(cm, "PCDATA state") == 0) { params.content_model.model = HUBBUB_CONTENT_MODEL_PCDATA; - } else if (strcmp(cm, "RCDATA") == 0) { + } else if (strcmp(cm, "RCDATA state") == 0) { params.content_model.model = HUBBUB_CONTENT_MODEL_RCDATA; - } else if (strcmp(cm, "CDATA") == 0) { + } else if (strcmp(cm, "CDATA state") == 0) { params.content_model.model = HUBBUB_CONTENT_MODEL_CDATA; + } else if (strcmp(cm, "RAWTEXT state") == 0) { + params.content_model.model = + HUBBUB_CONTENT_MODEL_RAWTEXT; } else { params.content_model.model = HUBBUB_CONTENT_MODEL_PLAINTEXT; diff --git a/test/tokeniser3.c b/test/tokeniser3.c index e68a230..86f079b 100644 --- a/test/tokeniser3.c +++ b/test/tokeniser3.c @@ -85,7 +85,7 @@ int main(int argc, char **argv) } else if (strcmp(key, "lastStartTag") == 0) { ctx.last_start_tag = (const char *) json_object_get_string(val); - } else if (strcmp(key, "contentModelFlags") == 0) { + } else if (strcmp(key, "initialStates") == 0) { ctx.content_model = json_object_get_array(val); } else if (strcmp(key, "processCDATA") == 0) { @@ -167,15 +167,18 @@ void run_test(context *ctx) (struct json_object *) array_list_get_idx(ctx->content_model, i)); - if (strcmp(cm, "PCDATA") == 0) { + if (strcmp(cm, "PCDATA state") == 0) { params.content_model.model = HUBBUB_CONTENT_MODEL_PCDATA; - } else if (strcmp(cm, "RCDATA") == 0) { + } else if (strcmp(cm, "RCDATA state") == 0) { params.content_model.model = HUBBUB_CONTENT_MODEL_RCDATA; - } else if (strcmp(cm, "CDATA") == 0) { + } else if (strcmp(cm, "CDATA state") == 0) { params.content_model.model = HUBBUB_CONTENT_MODEL_CDATA; + } else if (strcmp(cm, "RAWTEXT state") == 0) { + params.content_model.model = + HUBBUB_CONTENT_MODEL_RAWTEXT; } else { params.content_model.model = HUBBUB_CONTENT_MODEL_PLAINTEXT; -- HTML5 parser library