diff options
| -rw-r--r-- | CMakeLists.txt | 2 | ||||
| -rw-r--r-- | changelog.txt | 33 | ||||
| -rw-r--r-- | src/blocks.c | 212 | ||||
| -rw-r--r-- | src/chunk.h | 7 | ||||
| -rw-r--r-- | src/commonmark.c | 2 | ||||
| -rw-r--r-- | src/html.c | 8 | ||||
| -rw-r--r-- | src/inlines.c | 6 | ||||
| -rw-r--r-- | src/parser.h | 4 | ||||
| -rw-r--r-- | src/xml.c | 4 | ||||
| -rw-r--r-- | test/spec.txt | 20 |
10 files changed, 178 insertions, 120 deletions
diff --git a/CMakeLists.txt b/CMakeLists.txt index a4ebe92..7813ca1 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -9,7 +9,7 @@ endif() set(PROJECT_NAME "cmark") set(PROJECT_VERSION_MAJOR 0) -set(PROJECT_VERSION_MINOR 19) +set(PROJECT_VERSION_MINOR 20) set(PROJECT_VERSION_PATCH 0) set(PROJECT_VERSION ${PROJECT_VERSION_MAJOR}.${PROJECT_VERSION_MINOR}.${PROJECT_VERSION_PATCH} ) diff --git a/changelog.txt b/changelog.txt index e622f0b..9323ea1 100644 --- a/changelog.txt +++ b/changelog.txt @@ -1,3 +1,36 @@ +[0.20.0] + + * Fixed bug in list item parsing when items indented >= 4 spaces (#52). + * Don't allow link labels with no non-whitespace characters + (jgm/CommonMark#322). + * Fixed multiple issues with numeric entities (#33). + * Support CR and CRLF line endings (Ben Trask). + * Added test for different line endings to `api_test`. + * Allow NULL value in string setters (Nick Wellnhofer). (NULL + produces a 0-length string value.) Internally, URL and + title are now stored as `cmark_chunk` rather than `char *`. + * Fixed memory leak in `cmark_consolidate_text_nodes` (#32). + * Fixed `is_autolink` in the CommonMark renderer (#50). Previously *any* + link with an absolute URL was treated as an autolink. + * Cope with broken `snprintf` on Windows (Nick Wellnhofer). On Windows, + `snprintf` returns -1 if the output was truncated. Fall back to + Windows-specific `_scprintf`. + * Factored out `S_find_first_nonspace` in `S_proces_line`. + Added fields `offset`, `first_nonspace`, `indent`, and `blank` + to `cmark_parser` struct. This just removes some repetition. + * Added Racket Racket (5.3+) wrapper (Eli Barzilay). + * Removed -pg from Debug build flags (#47). + * Added Ubsan build target, to check for undefined behavior. + * Improved `make leakcheck`. We now return an error status if anything + in the loop fails. We now check `--smart` and `--normalize` options. + * Removed `wrapper3.py`, made `wrapper.py` work with python 2 and 3. + Also improved the wrapper to work with Windows, and to use smart + punctuation (as an example). + * In `wrapper.rb`, added argument for options. + * Revised luajit wrapper. + * Added build status badges to README.md. + * Added links to go, perl, ruby, R, and Haskell bindings to README.md. + [0.19.0] * Fixed `_` emphasis parsing to conform to spec (jgm/CommonMark#317). diff --git a/src/blocks.c b/src/blocks.c index 8ccaa25..b72c256 100644 --- a/src/blocks.c +++ b/src/blocks.c @@ -19,7 +19,7 @@ #define peek_at(i, n) (i)->data[n] static inline bool -is_line_end_char(char c) +S_is_line_end_char(char c) { return (c == '\n' || c == '\r'); } @@ -69,6 +69,10 @@ cmark_parser *cmark_parser_new(int options) parser->root = document; parser->current = document; parser->line_number = 0; + parser->offset = 0; + parser->first_nonspace = 0; + parser->indent = 0; + parser->blank = false; parser->curline = line; parser->last_line_length = 0; parser->linebuf = buf; @@ -138,7 +142,7 @@ static void remove_trailing_blank_lines(cmark_strbuf *ln) for (i = ln->size - 1; i >= 0; --i) { c = ln->ptr[i]; - if (c != ' ' && c != '\t' && !is_line_end_char(c)) + if (c != ' ' && c != '\t' && !S_is_line_end_char(c)) break; } @@ -151,7 +155,7 @@ static void remove_trailing_blank_lines(cmark_strbuf *ln) for(; i < ln->size; ++i) { c = ln->ptr[i]; - if (!is_line_end_char(c)) + if (!S_is_line_end_char(c)) continue; cmark_strbuf_truncate(ln, i); @@ -249,7 +253,7 @@ finalize(cmark_parser *parser, cmark_node* b) // first line of contents becomes info for (pos = 0; pos < b->string_content.size; ++pos) { - if (is_line_end_char(b->string_content.ptr[pos])) + if (S_is_line_end_char(b->string_content.ptr[pos])) break; } assert(pos < b->string_content.size); @@ -495,7 +499,7 @@ S_parser_feed(cmark_parser *parser, const unsigned char *buffer, size_t len, size_t line_len; for (eol = buffer; eol < end; ++eol) { - if (is_line_end_char(*eol)) + if (S_is_line_end_char(*eol)) break; } if (eol >= end) @@ -546,29 +550,39 @@ static void chop_trailing_hashtags(cmark_chunk *ch) } static void +S_find_first_nonspace(cmark_parser *parser, cmark_chunk *input) +{ + parser->first_nonspace = parser->offset; + while (peek_at(input, parser->first_nonspace) == ' ') { + parser->first_nonspace++; + } + + parser->indent = parser->first_nonspace - parser->offset; + parser->blank = S_is_line_end_char(peek_at(input, parser->first_nonspace)); +} + +static void S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes) { cmark_node* last_matched_container; - int offset = 0; int matched = 0; int lev = 0; int i; cmark_list *data = NULL; bool all_matched = true; cmark_node* container; - bool blank = false; - int first_nonspace; - int indent; bool indented; cmark_chunk input; bool maybe_lazy; utf8proc_detab(parser->curline, buffer, bytes); + parser->offset = 0; + parser->blank = false; // Add a newline to the end if not present: // TODO this breaks abstraction: if (parser->curline->size > 0 && - !is_line_end_char(parser->curline->ptr[parser->curline->size - 1])) { + !S_is_line_end_char(parser->curline->ptr[parser->curline->size - 1])) { cmark_strbuf_putc(parser->curline, '\n'); } @@ -586,32 +600,26 @@ S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes) while (container->last_child && container->last_child->open) { container = container->last_child; - first_nonspace = offset; - while (peek_at(&input, first_nonspace) == ' ') { - first_nonspace++; - } - - indent = first_nonspace - offset; - blank = is_line_end_char(peek_at(&input, first_nonspace)); + S_find_first_nonspace(parser, &input); if (container->type == NODE_BLOCK_QUOTE) { - matched = indent <= 3 && peek_at(&input, first_nonspace) == '>'; + matched = parser->indent <= 3 && peek_at(&input, parser->first_nonspace) == '>'; if (matched) { - offset = first_nonspace + 1; - if (peek_at(&input, offset) == ' ') - offset++; + parser->offset = parser->first_nonspace + 1; + if (peek_at(&input, parser->offset) == ' ') + parser->offset++; } else { all_matched = false; } } else if (container->type == NODE_ITEM) { - if (indent >= container->as.list.marker_offset + + if (parser->indent >= container->as.list.marker_offset + container->as.list.padding) { - offset += container->as.list.marker_offset + + parser->offset += container->as.list.marker_offset + container->as.list.padding; - } else if (blank) { - offset = first_nonspace; + } else if (parser->blank) { + parser->offset = parser->first_nonspace; } else { all_matched = false; } @@ -619,34 +627,34 @@ S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes) } else if (container->type == NODE_CODE_BLOCK) { if (!container->as.code.fenced) { // indented - if (indent >= CODE_INDENT) { - offset += CODE_INDENT; - } else if (blank) { - offset = first_nonspace; + if (parser->indent >= CODE_INDENT) { + parser->offset += CODE_INDENT; + } else if (parser->blank) { + parser->offset = parser->first_nonspace; } else { all_matched = false; } } else { // fenced matched = 0; - if (indent <= 3 && - (peek_at(&input, first_nonspace) == + if (parser->indent <= 3 && + (peek_at(&input, parser->first_nonspace) == container->as.code.fence_char)) { matched = scan_close_code_fence(&input, - first_nonspace); + parser->first_nonspace); } if (matched >= container->as.code.fence_length) { // closing fence - and since we're at // the end of a line, we can return: all_matched = false; - offset += matched; + parser->offset += matched; parser->current = finalize(parser, container); goto finished; } else { - // skip opt. spaces of fence offset + // skip opt. spaces of fence parser->offset i = container->as.code.fence_offset; while (i > 0 && - peek_at(&input, offset) == ' ') { - offset++; + peek_at(&input, parser->offset) == ' ') { + parser->offset++; i--; } } @@ -658,13 +666,13 @@ S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes) } else if (container->type == NODE_HTML) { - if (blank) { + if (parser->blank) { all_matched = false; } } else if (container->type == NODE_PARAGRAPH) { - if (blank) { + if (parser->blank) { all_matched = false; } @@ -679,7 +687,7 @@ S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes) last_matched_container = container; // check to see if we've hit 2nd blank line, break out of list: - if (blank && container->last_line_blank) { + if (parser->blank && container->last_line_blank) { break_out_of_lists(parser, &container); } @@ -688,37 +696,23 @@ S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes) while (container->type != NODE_CODE_BLOCK && container->type != NODE_HTML) { - first_nonspace = offset; - while (peek_at(&input, first_nonspace) == ' ') - first_nonspace++; - - indent = first_nonspace - offset; - indented = indent >= CODE_INDENT; - blank = is_line_end_char(peek_at(&input, first_nonspace)); + S_find_first_nonspace(parser, &input); + indented = parser->indent >= CODE_INDENT; - if (indented && !maybe_lazy && !blank) { - offset += CODE_INDENT; - container = add_child(parser, container, NODE_CODE_BLOCK, offset + 1); - container->as.code.fenced = false; - container->as.code.fence_char = 0; - container->as.code.fence_length = 0; - container->as.code.fence_offset = 0; - container->as.code.info = cmark_chunk_literal(""); + if (!indented && peek_at(&input, parser->first_nonspace) == '>') { - } else if (!indented && peek_at(&input, first_nonspace) == '>') { - - offset = first_nonspace + 1; + parser->offset = parser->first_nonspace + 1; // optional following character - if (peek_at(&input, offset) == ' ') - offset++; - container = add_child(parser, container, NODE_BLOCK_QUOTE, offset + 1); + if (peek_at(&input, parser->offset) == ' ') + parser->offset++; + container = add_child(parser, container, NODE_BLOCK_QUOTE, parser->offset + 1); - } else if (!indented && (matched = scan_atx_header_start(&input, first_nonspace))) { + } else if (!indented && (matched = scan_atx_header_start(&input, parser->first_nonspace))) { - offset = first_nonspace + matched; - container = add_child(parser, container, NODE_HEADER, offset + 1); + parser->offset = parser->first_nonspace + matched; + container = add_child(parser, container, NODE_HEADER, parser->offset + 1); - int hashpos = cmark_chunk_strchr(&input, '#', first_nonspace); + int hashpos = cmark_chunk_strchr(&input, '#', parser->first_nonspace); int level = 0; while (peek_at(&input, hashpos) == '#') { @@ -728,24 +722,24 @@ S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes) container->as.header.level = level; container->as.header.setext = false; - } else if (!indented && (matched = scan_open_code_fence(&input, first_nonspace))) { + } else if (!indented && (matched = scan_open_code_fence(&input, parser->first_nonspace))) { - container = add_child(parser, container, NODE_CODE_BLOCK, first_nonspace + 1); + container = add_child(parser, container, NODE_CODE_BLOCK, parser->first_nonspace + 1); container->as.code.fenced = true; - container->as.code.fence_char = peek_at(&input, first_nonspace); + container->as.code.fence_char = peek_at(&input, parser->first_nonspace); container->as.code.fence_length = matched; - container->as.code.fence_offset = first_nonspace - offset; + container->as.code.fence_offset = parser->first_nonspace - parser->offset; container->as.code.info = cmark_chunk_literal(""); - offset = first_nonspace + matched; + parser->offset = parser->first_nonspace + matched; - } else if (!indented && (matched = scan_html_block_tag(&input, first_nonspace))) { + } else if (!indented && (matched = scan_html_block_tag(&input, parser->first_nonspace))) { - container = add_child(parser, container, NODE_HTML, first_nonspace + 1); - // note, we don't adjust offset because the tag is part of the text + container = add_child(parser, container, NODE_HTML, parser->first_nonspace + 1); + // note, we don't adjust parser->offset because the tag is part of the text } else if (!indented && - container->type == NODE_PARAGRAPH && - (lev = scan_setext_header_line(&input, first_nonspace)) && + container->type == NODE_PARAGRAPH && + (lev = scan_setext_header_line(&input, parser->first_nonspace)) && // check that there is only one line in the paragraph: (cmark_strbuf_strrchr(&container->string_content, '\n', cmark_strbuf_len(&container->string_content) - 2) < 0)) { @@ -753,57 +747,70 @@ S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes) container->type = NODE_HEADER; container->as.header.level = lev; container->as.header.setext = true; - offset = input.len - 1; + parser->offset = input.len - 1; } else if (!indented && - !(container->type == NODE_PARAGRAPH && - !all_matched) && - (matched = scan_hrule(&input, first_nonspace))) { + !(container->type == NODE_PARAGRAPH && + !all_matched) && + (matched = scan_hrule(&input, parser->first_nonspace))) { // it's only now that we know the line is not part of a setext header: - container = add_child(parser, container, NODE_HRULE, first_nonspace + 1); + container = add_child(parser, container, NODE_HRULE, parser->first_nonspace + 1); container = finalize(parser, container); - offset = input.len - 1; + parser->offset = input.len - 1; - } else if ((matched = parse_list_marker(&input, first_nonspace, &data))) { + } else if ((matched = parse_list_marker(&input, parser->first_nonspace, &data)) && + (!indented || container->type == NODE_LIST)) { + // Note that we can have new list items starting with >= 4 + // spaces indent, as long as the list container is still open. // compute padding: - offset = first_nonspace + matched; + parser->offset = parser->first_nonspace + matched; i = 0; - while (i <= 5 && peek_at(&input, offset + i) == ' ') { + while (i <= 5 && peek_at(&input, parser->offset + i) == ' ') { i++; } // i = number of spaces after marker, up to 5 if (i >= 5 || i < 1 || - is_line_end_char(peek_at(&input, offset))) { + S_is_line_end_char(peek_at(&input, parser->offset))) { data->padding = matched + 1; if (i > 0) { - offset += 1; + parser->offset += 1; } } else { data->padding = matched + i; - offset += i; + parser->offset += i; } // check container; if it's a list, see if this list item // can continue the list; otherwise, create a list container. - data->marker_offset = indent; + data->marker_offset = parser->indent; if (container->type != NODE_LIST || !lists_match(&container->as.list, data)) { container = add_child(parser, container, NODE_LIST, - first_nonspace + 1); + parser->first_nonspace + 1); memcpy(&container->as.list, data, sizeof(*data)); } // add the list item container = add_child(parser, container, NODE_ITEM, - first_nonspace + 1); + parser->first_nonspace + 1); /* TODO: static */ memcpy(&container->as.list, data, sizeof(*data)); free(data); + + } else if (indented && !maybe_lazy && !parser->blank) { + parser->offset += CODE_INDENT; + container = add_child(parser, container, NODE_CODE_BLOCK, parser->offset + 1); + container->as.code.fenced = false; + container->as.code.fence_char = 0; + container->as.code.fence_length = 0; + container->as.code.fence_offset = 0; + container->as.code.info = cmark_chunk_literal(""); + } else { break; } @@ -815,17 +822,12 @@ S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes) maybe_lazy = false; } - // what remains at offset is a text line. add the text to the + // what remains at parser->offset is a text line. add the text to the // appropriate container. - first_nonspace = offset; - while (peek_at(&input, first_nonspace) == ' ') - first_nonspace++; - - indent = first_nonspace - offset; - blank = is_line_end_char(peek_at(&input, first_nonspace)); + S_find_first_nonspace(parser, &input); - if (blank && container->last_child) { + if (parser->blank && container->last_child) { container->last_child->last_line_blank = true; } @@ -833,7 +835,7 @@ S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes) // and we don't count blanks in fenced code for purposes of tight/loose // lists or breaking out of lists. we also don't set last_line_blank // on an empty list item. - container->last_line_blank = (blank && + container->last_line_blank = (parser->blank && container->type != NODE_BLOCK_QUOTE && container->type != NODE_HEADER && !(container->type == NODE_CODE_BLOCK && @@ -850,11 +852,11 @@ S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes) if (parser->current != last_matched_container && container == last_matched_container && - !blank && + !parser->blank && parser->current->type == NODE_PARAGRAPH && cmark_strbuf_len(&parser->current->string_content) > 0) { - add_line(parser->current, &input, offset); + add_line(parser->current, &input, parser->offset); } else { // not a lazy continuation @@ -867,9 +869,9 @@ S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes) if (container->type == NODE_CODE_BLOCK || container->type == NODE_HTML) { - add_line(container, &input, offset); + add_line(container, &input, parser->offset); - } else if (blank) { + } else if (parser->blank) { // ??? do nothing @@ -879,12 +881,12 @@ S_process_line(cmark_parser *parser, const unsigned char *buffer, size_t bytes) container->as.header.setext == false) { chop_trailing_hashtags(&input); } - add_line(container, &input, first_nonspace); + add_line(container, &input, parser->first_nonspace); } else { // create paragraph container for line - container = add_child(parser, container, NODE_PARAGRAPH, first_nonspace + 1); - add_line(container, &input, first_nonspace); + container = add_child(parser, container, NODE_PARAGRAPH, parser->first_nonspace + 1); + add_line(container, &input, parser->first_nonspace); } diff --git a/src/chunk.h b/src/chunk.h index 4bb4980..a246a9d 100644 --- a/src/chunk.h +++ b/src/chunk.h @@ -66,8 +66,8 @@ static inline const char *cmark_chunk_to_cstr(cmark_chunk *c) } str = (unsigned char *)malloc(c->len + 1); if(str != NULL) { - if(c->len > 0){ - memcpy(str, c->data, c->len); + if(c->len > 0) { + memcpy(str, c->data, c->len); } str[c->len] = 0; } @@ -86,8 +86,7 @@ static inline void cmark_chunk_set_cstr(cmark_chunk *c, const char *str) c->len = 0; c->data = NULL; c->alloc = 0; - } - else { + } else { c->len = strlen(str); c->data = (unsigned char *)malloc(c->len + 1); c->alloc = 1; diff --git a/src/commonmark.c b/src/commonmark.c index 47da191..dba1fcf 100644 --- a/src/commonmark.c +++ b/src/commonmark.c @@ -260,7 +260,7 @@ is_autolink(cmark_node *node) link_text = node->first_child; cmark_consolidate_text_nodes(link_text); return ((int)strlen(url) == link_text->as.literal.len && - strncmp(url, + strncmp(url, (char*)link_text->as.literal.data, link_text->as.literal.len) == 0); } @@ -262,12 +262,12 @@ S_render_node(cmark_node *node, cmark_event_type ev_type, if (entering) { cmark_strbuf_puts(html, "<a href=\""); escape_href(html, node->as.link.url.data, - node->as.link.url.len); + node->as.link.url.len); if (node->as.link.title.len) { cmark_strbuf_puts(html, "\" title=\""); escape_html(html, node->as.link.title.data, - node->as.link.title.len); + node->as.link.title.len); } cmark_strbuf_puts(html, "\">"); @@ -280,7 +280,7 @@ S_render_node(cmark_node *node, cmark_event_type ev_type, if (entering) { cmark_strbuf_puts(html, "<img src=\""); escape_href(html, node->as.link.url.data, - node->as.link.url.len); + node->as.link.url.len); cmark_strbuf_puts(html, "\" alt=\""); state->plain = node; @@ -288,7 +288,7 @@ S_render_node(cmark_node *node, cmark_event_type ev_type, if (node->as.link.title.len) { cmark_strbuf_puts(html, "\" title=\""); escape_html(html, node->as.link.title.data, - node->as.link.title.len); + node->as.link.title.len); } cmark_strbuf_puts(html, "\" />"); diff --git a/src/inlines.c b/src/inlines.c index 352ded3..8a1ee44 100644 --- a/src/inlines.c +++ b/src/inlines.c @@ -151,7 +151,7 @@ static cmark_chunk chunk_clone(cmark_chunk *src) memcpy(c.data, src->data, len); c.data[len] = '\0'; - return c; + return c; } static void subject_from_buf(subject *e, cmark_strbuf *buffer, @@ -307,9 +307,9 @@ scan_delims(subject* subj, unsigned char c, bool * can_open, bool * can_close) !utf8proc_is_punctuation(after_char)); if (c == '_') { *can_open = left_flanking && - (!right_flanking || utf8proc_is_punctuation(before_char)); + (!right_flanking || utf8proc_is_punctuation(before_char)); *can_close = right_flanking && - (!left_flanking || utf8proc_is_punctuation(after_char)); + (!left_flanking || utf8proc_is_punctuation(after_char)); } else if (c == '\'' || c == '"') { *can_open = left_flanking && !right_flanking; *can_close = right_flanking; diff --git a/src/parser.h b/src/parser.h index cbccae3..ccdf84b 100644 --- a/src/parser.h +++ b/src/parser.h @@ -16,6 +16,10 @@ struct cmark_parser { struct cmark_node* root; struct cmark_node* current; int line_number; + int offset; + int first_nonspace; + int indent; + bool blank; cmark_strbuf *curline; int last_line_length; cmark_strbuf *linebuf; @@ -119,11 +119,11 @@ S_render_node(cmark_node *node, cmark_event_type ev_type, case CMARK_NODE_IMAGE: cmark_strbuf_puts(xml, " destination=\""); escape_xml(xml, node->as.link.url.data, - node->as.link.url.len); + node->as.link.url.len); cmark_strbuf_putc(xml, '"'); cmark_strbuf_puts(xml, " title=\""); escape_xml(xml, node->as.link.title.data, - node->as.link.title.len); + node->as.link.title.len); cmark_strbuf_putc(xml, '"'); break; default: diff --git a/test/spec.txt b/test/spec.txt index 13db0ab..ba2c5aa 100644 --- a/test/spec.txt +++ b/test/spec.txt @@ -3858,6 +3858,26 @@ item: </ul> . +. +1. a + + 2. b + + 3. c +. +<ol> +<li> +<p>a</p> +</li> +<li> +<p>b</p> +</li> +<li> +<p>c</p> +</li> +</ol> +. + This is a loose list, because there is a blank line between two of the list items: |