diff options
Diffstat (limited to 'src')
| -rw-r--r-- | src/blocks.c | 201 | ||||
| -rw-r--r-- | src/buffer.c | 11 | ||||
| -rw-r--r-- | src/inlines.c | 465 | ||||
| -rw-r--r-- | src/main.c | 5 | ||||
| -rw-r--r-- | src/print.c | 34 | ||||
| -rw-r--r-- | src/references.c | 9 | ||||
| -rw-r--r-- | src/stmd.h | 2 | ||||
| -rw-r--r-- | src/utf8.c | 39 |
8 files changed, 376 insertions, 390 deletions
diff --git a/src/blocks.c b/src/blocks.c index 024b8f0..8d6fd06 100644 --- a/src/blocks.c +++ b/src/blocks.c @@ -47,13 +47,13 @@ bool is_blank(strbuf *s, int offset) { while (offset < s->size) { switch (s->ptr[offset]) { - case '\n': - return true; - case ' ': - offset++; - break; - default: - return false; + case '\n': + return true; + case ' ': + offset++; + break; + default: + return false; } } @@ -63,17 +63,17 @@ bool is_blank(strbuf *s, int offset) static inline bool can_contain(int parent_type, int child_type) { return ( parent_type == BLOCK_DOCUMENT || - parent_type == BLOCK_BQUOTE || - parent_type == BLOCK_LIST_ITEM || - (parent_type == BLOCK_LIST && child_type == BLOCK_LIST_ITEM) ); + parent_type == BLOCK_BQUOTE || + parent_type == BLOCK_LIST_ITEM || + (parent_type == BLOCK_LIST && child_type == BLOCK_LIST_ITEM) ); } static inline bool accepts_lines(int block_type) { return (block_type == BLOCK_PARAGRAPH || - block_type == BLOCK_ATX_HEADER || - block_type == BLOCK_INDENTED_CODE || - block_type == BLOCK_FENCED_CODE); + block_type == BLOCK_ATX_HEADER || + block_type == BLOCK_INDENTED_CODE || + block_type == BLOCK_FENCED_CODE); } static void add_line(node_block* node_block, chunk *ch, int offset) @@ -87,7 +87,7 @@ static void remove_trailing_blank_lines(strbuf *ln) int i; for (i = ln->size - 1; i >= 0; --i) { - char c = ln->ptr[i]; + unsigned char c = ln->ptr[i]; if (c != ' ' && c != '\t' && c != '\r' && c != '\n') break; @@ -156,77 +156,77 @@ static void finalize(node_block* b, int line_number) } switch (b->tag) { - case BLOCK_PARAGRAPH: - pos = 0; - while (strbuf_at(&b->string_content, 0) == '[' && - (pos = parse_reference_inline(&b->string_content, b->top->as.document.refmap))) { - - strbuf_drop(&b->string_content, pos); - } - if (is_blank(&b->string_content, 0)) { - b->tag = BLOCK_REFERENCE_DEF; - } - break; + case BLOCK_PARAGRAPH: + pos = 0; + while (strbuf_at(&b->string_content, 0) == '[' && + (pos = parse_reference_inline(&b->string_content, b->top->as.document.refmap))) { - case BLOCK_INDENTED_CODE: - remove_trailing_blank_lines(&b->string_content); - strbuf_putc(&b->string_content, '\n'); - break; - - case BLOCK_FENCED_CODE: - // first line of contents becomes info - firstlinelen = strbuf_strchr(&b->string_content, '\n', 0); - - strbuf_init(&b->as.code.info, 0); - houdini_unescape_html_f( - &b->as.code.info, - b->string_content.ptr, - firstlinelen + strbuf_drop(&b->string_content, pos); + } + if (is_blank(&b->string_content, 0)) { + b->tag = BLOCK_REFERENCE_DEF; + } + break; + + case BLOCK_INDENTED_CODE: + remove_trailing_blank_lines(&b->string_content); + strbuf_putc(&b->string_content, '\n'); + break; + + case BLOCK_FENCED_CODE: + // first line of contents becomes info + firstlinelen = strbuf_strchr(&b->string_content, '\n', 0); + + strbuf_init(&b->as.code.info, 0); + houdini_unescape_html_f( + &b->as.code.info, + b->string_content.ptr, + firstlinelen ); - strbuf_drop(&b->string_content, firstlinelen + 1); + strbuf_drop(&b->string_content, firstlinelen + 1); - strbuf_trim(&b->as.code.info); - strbuf_unescape(&b->as.code.info); - break; + strbuf_trim(&b->as.code.info); + strbuf_unescape(&b->as.code.info); + break; - case BLOCK_LIST: // determine tight/loose status - b->as.list.tight = true; // tight by default - item = b->children; + case BLOCK_LIST: // determine tight/loose status + b->as.list.tight = true; // tight by default + item = b->children; - while (item) { - // check for non-final non-empty list item ending with blank line: - if (item->last_line_blank && item->next) { + while (item) { + // check for non-final non-empty list item ending with blank line: + if (item->last_line_blank && item->next) { + b->as.list.tight = false; + break; + } + // recurse into children of list item, to see if there are + // spaces between them: + subitem = item->children; + while (subitem) { + if (ends_with_blank_line(subitem) && + (item->next || subitem->next)) { b->as.list.tight = false; break; } - // recurse into children of list item, to see if there are - // spaces between them: - subitem = item->children; - while (subitem) { - if (ends_with_blank_line(subitem) && - (item->next || subitem->next)) { - b->as.list.tight = false; - break; - } - subitem = subitem->next; - } - if (!(b->as.list.tight)) { - break; - } - item = item->next; + subitem = subitem->next; } + if (!(b->as.list.tight)) { + break; + } + item = item->next; + } - break; + break; - default: - break; + default: + break; } } // Add a node_block as child of another. Return pointer to child. static node_block* add_child(node_block* parent, - int block_type, int start_line, int start_column) + int block_type, int start_line, int start_column) { assert(parent); @@ -276,14 +276,14 @@ void stmd_free_nodes(node_block *e) void process_inlines(node_block* cur, reference_map *refmap) { switch (cur->tag) { - case BLOCK_PARAGRAPH: - case BLOCK_ATX_HEADER: - case BLOCK_SETEXT_HEADER: - cur->inline_content = parse_inlines(&cur->string_content, refmap); - break; - - default: - break; + case BLOCK_PARAGRAPH: + case BLOCK_ATX_HEADER: + case BLOCK_SETEXT_HEADER: + cur->inline_content = parse_inlines(&cur->string_content, refmap); + break; + + default: + break; } node_block *child = cur->children; @@ -362,9 +362,9 @@ static int parse_list_marker(chunk *input, int pos, struct ListData ** dataptr) static int lists_match(struct ListData *list_data, struct ListData *item_data) { return (list_data->list_type == item_data->list_type && - list_data->delimiter == item_data->delimiter && - // list_data->marker_offset == item_data.marker_offset && - list_data->bullet_char == item_data->bullet_char); + list_data->delimiter == item_data->delimiter && + // list_data->marker_offset == item_data.marker_offset && + list_data->bullet_char == item_data->bullet_char); } static node_block *finalize_document(node_block *document, int linenum) @@ -493,7 +493,7 @@ static void incorporate_line(strbuf *line, int line_number, node_block** curptr) } else if (container->tag == BLOCK_LIST_ITEM) { if (indent >= container->as.list.marker_offset + - container->as.list.padding) { + container->as.list.padding) { offset += container->as.list.marker_offset + container->as.list.padding; } else if (blank) { @@ -513,7 +513,7 @@ static void incorporate_line(strbuf *line, int line_number, node_block** curptr) } } else if (container->tag == BLOCK_ATX_HEADER || - container->tag == BLOCK_SETEXT_HEADER) { + container->tag == BLOCK_SETEXT_HEADER) { // a header can never contain more than one line all_matched = false; @@ -557,7 +557,7 @@ static void incorporate_line(strbuf *line, int line_number, node_block** curptr) // unless last matched container is code node_block, try new container starts: while (container->tag != BLOCK_FENCED_CODE && container->tag != BLOCK_INDENTED_CODE && - container->tag != BLOCK_HTML) { + container->tag != BLOCK_HTML) { first_nonspace = offset; while (peek_at(&input, first_nonspace) == ' ') @@ -610,17 +610,17 @@ static void incorporate_line(strbuf *line, int line_number, node_block** curptr) // note, we don't adjust offset because the tag is part of the text } else if (container->tag == BLOCK_PARAGRAPH && - (lev = scan_setext_header_line(&input, first_nonspace)) && - // check that there is only one line in the paragraph: - strbuf_strrchr(&container->string_content, '\n', - strbuf_len(&container->string_content) - 2) < 0) { + (lev = scan_setext_header_line(&input, first_nonspace)) && + // check that there is only one line in the paragraph: + strbuf_strrchr(&container->string_content, '\n', + strbuf_len(&container->string_content) - 2) < 0) { container->tag = BLOCK_SETEXT_HEADER; container->as.header.level = lev; offset = input.len - 1; } else if (!(container->tag == BLOCK_PARAGRAPH && !all_matched) && - (matched = scan_hrule(&input, first_nonspace))) { + (matched = scan_hrule(&input, first_nonspace))) { // it's only now that we know the line is not part of a setext header: container = add_child(container, BLOCK_HRULE, line_number, first_nonspace + 1); @@ -653,16 +653,16 @@ static void incorporate_line(strbuf *line, int line_number, node_block** curptr) data->marker_offset = indent; if (container->tag != BLOCK_LIST || - !lists_match(&container->as.list, data)) { + !lists_match(&container->as.list, data)) { container = add_child(container, BLOCK_LIST, line_number, - first_nonspace + 1); + first_nonspace + 1); memcpy(&container->as.list, data, sizeof(*data)); } // add the list item container = add_child(container, BLOCK_LIST_ITEM, line_number, - first_nonspace + 1); + first_nonspace + 1); /* TODO: static */ memcpy(&container->as.list, data, sizeof(*data)); free(data); @@ -691,11 +691,11 @@ static void incorporate_line(strbuf *line, int line_number, node_block** curptr) // 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->tag != BLOCK_BQUOTE && - container->tag != BLOCK_FENCED_CODE && - !(container->tag == BLOCK_LIST_ITEM && - container->children == NULL && - container->start_line == line_number)); + container->tag != BLOCK_BQUOTE && + container->tag != BLOCK_FENCED_CODE && + !(container->tag == BLOCK_LIST_ITEM && + container->children == NULL && + container->start_line == line_number)); node_block *cont = container; while (cont->parent) { @@ -704,10 +704,10 @@ static void incorporate_line(strbuf *line, int line_number, node_block** curptr) } if (cur != last_matched_container && - container == last_matched_container && - !blank && - cur->tag == BLOCK_PARAGRAPH && - strbuf_len(&cur->string_content) > 0) { + container == last_matched_container && + !blank && + cur->tag == BLOCK_PARAGRAPH && + strbuf_len(&cur->string_content) > 0) { add_line(cur, &input, offset); @@ -728,7 +728,7 @@ static void incorporate_line(strbuf *line, int line_number, node_block** curptr) matched = 0; if (indent <= 3 && - peek_at(&input, first_nonspace) == container->as.code.fence_char) { + peek_at(&input, first_nonspace) == container->as.code.fence_char) { int fence_len = scan_close_code_fence(&input, first_nonspace); if (fence_len > container->as.code.fence_length) matched = 1; @@ -774,4 +774,3 @@ static void incorporate_line(strbuf *line, int line_number, node_block** curptr) *curptr = container; } } - diff --git a/src/buffer.c b/src/buffer.c index 7c2b86b..2e32720 100644 --- a/src/buffer.c +++ b/src/buffer.c @@ -15,8 +15,8 @@ unsigned char strbuf__initbuf[1]; unsigned char strbuf__oom[1]; -#define ENSURE_SIZE(b, d) \ - if ((d) > buf->asize && strbuf_grow(b, (d)) < 0)\ +#define ENSURE_SIZE(b, d) \ + if ((d) > buf->asize && strbuf_grow(b, (d)) < 0) \ return -1; void strbuf_init(strbuf *buf, int initial_size) @@ -111,8 +111,8 @@ int strbuf_set(strbuf *buf, const unsigned char *data, int len) int strbuf_sets(strbuf *buf, const char *string) { return strbuf_set(buf, - (const unsigned char *)string, - string ? strlen(string) : 0); + (const unsigned char *)string, + string ? strlen(string) : 0); } int strbuf_putc(strbuf *buf, int c) @@ -155,7 +155,7 @@ int strbuf_vprintf(strbuf *buf, const char *format, va_list ap) (char *)buf->ptr + buf->size, buf->asize - buf->size, format, args - ); + ); if (len < 0) { free(buf->ptr); @@ -351,4 +351,3 @@ extern void strbuf_unescape(strbuf *buf) strbuf_truncate(buf, w); } - diff --git a/src/inlines.c b/src/inlines.c index f5c8e7b..4744312 100644 --- a/src/inlines.c +++ b/src/inlines.c @@ -10,11 +10,19 @@ #include "scanners.h" #include "inlines.h" +typedef struct InlineStack { + struct InlineStack *previous; + node_inl *first_inline; + int delim_count; + unsigned char delim_char; +} inline_stack; + typedef struct Subject { chunk input; int pos; int label_nestlevel; reference_map *refmap; + inline_stack *emphasis_openers; } subject; static node_inl *parse_chunk_inlines(chunk *chunk, reference_map *refmap); @@ -118,26 +126,26 @@ extern void free_inlines(node_inl* e) node_inl * next; while (e != NULL) { switch (e->tag){ - case INL_STRING: - case INL_RAW_HTML: - case INL_CODE: - chunk_free(&e->content.literal); - break; - case INL_LINEBREAK: - case INL_SOFTBREAK: - break; - case INL_LINK: - case INL_IMAGE: - free(e->content.linkable.url); - free(e->content.linkable.title); - free_inlines(e->content.linkable.label); - break; - case INL_EMPH: - case INL_STRONG: - free_inlines(e->content.inlines); - break; - default: - break; + case INL_STRING: + case INL_RAW_HTML: + case INL_CODE: + chunk_free(&e->content.literal); + break; + case INL_LINEBREAK: + case INL_SOFTBREAK: + break; + case INL_LINK: + case INL_IMAGE: + free(e->content.linkable.url); + free(e->content.linkable.title); + free_inlines(e->content.linkable.label); + break; + case INL_EMPH: + case INL_STRONG: + free_inlines(e->content.inlines); + break; + default: + break; } next = e->next; free(e); @@ -168,6 +176,7 @@ static void subject_from_buf(subject *e, strbuf *buffer, reference_map *refmap) e->pos = 0; e->label_nestlevel = 0; e->refmap = refmap; + e->emphasis_openers = NULL; chunk_rtrim(&e->input); } @@ -180,6 +189,7 @@ static void subject_from_chunk(subject *e, chunk *chunk, reference_map *refmap) e->pos = 0; e->label_nestlevel = 0; e->refmap = refmap; + e->emphasis_openers = NULL; chunk_rtrim(&e->input); } @@ -231,7 +241,7 @@ inline static chunk take_while(subject* subj, int (*f)(int)) static int scan_to_closing_backticks(subject* subj, int openticklength) { // read non backticks - char c; + unsigned char c; while ((c = peek_char(subj)) && c != '`') { advance(subj); } @@ -272,12 +282,11 @@ static node_inl* handle_backticks(subject *subj) } // Scan ***, **, or * and return number scanned, or 0. -// Don't advance position. -static int scan_delims(subject* subj, char c, bool * can_open, bool * can_close) +// Advances position. +static int scan_delims(subject* subj, unsigned char c, bool * can_open, bool * can_close) { int numdelims = 0; - char char_before, char_after; - int startpos = subj->pos; + unsigned char char_before, char_after; char_before = subj->pos == 0 ? '\n' : peek_at(subj, subj->pos - 1); while (peek_char(subj) == c) { @@ -291,132 +300,109 @@ static int scan_delims(subject* subj, char c, bool * can_open, bool * can_close) *can_open = *can_open && !isalnum(char_before); *can_close = *can_close && !isalnum(char_after); } - subj->pos = startpos; return numdelims; } +static void free_openers(subject* subj, inline_stack* istack) +{ + inline_stack * tempstack; + while (subj->emphasis_openers != istack) { + tempstack = subj->emphasis_openers; + subj->emphasis_openers = subj->emphasis_openers->previous; + free(tempstack); + } +} + // Parse strong/emph or a fallback. // Assumes the subject has '_' or '*' at the current position. -static node_inl* handle_strong_emph(subject* subj, char c) +static node_inl* handle_strong_emph(subject* subj, unsigned char c, node_inl **last) { bool can_open, can_close; - node_inl * result = NULL; - node_inl * last = NULL; - node_inl * new; - node_inl * il; - node_inl * first_head = NULL; - node_inl * first_close = NULL; - int first_close_delims = 0; int numdelims; + int useDelims; + inline_stack * istack; + node_inl * inl; + node_inl * emph; + node_inl * inl_text; numdelims = scan_delims(subj, c, &can_open, &can_close); - subj->pos += numdelims; - - new = make_str(chunk_dup(&subj->input, subj->pos - numdelims, numdelims)); - last = new; - first_head = new; - result = new; - - if (!can_open || numdelims == 0) { - goto done; - } - - switch (numdelims) { - case 1: - while (true) { - numdelims = scan_delims(subj, c, &can_open, &can_close); - if (numdelims >= 1 && can_close) { - subj->pos += 1; - first_head->tag = INL_EMPH; - chunk_free(&first_head->content.literal); - first_head->content.inlines = first_head->next; - first_head->next = NULL; - goto done; - } else { - if (!parse_inline(subj, &last)) { - goto done; - } - } - } - break; - case 2: - while (true) { - numdelims = scan_delims(subj, c, &can_open, &can_close); - if (numdelims >= 2 && can_close) { - subj->pos += 2; - first_head->tag = INL_STRONG; - chunk_free(&first_head->content.literal); - first_head->content.inlines = first_head->next; - first_head->next = NULL; - goto done; - } else { - if (!parse_inline(subj, &last)) { - goto done; - } - } - } - break; - case 3: - while (true) { - numdelims = scan_delims(subj, c, &can_open, &can_close); - if (can_close && numdelims >= 1 && numdelims <= 3 && - numdelims != first_close_delims) { - new = make_str(chunk_dup(&subj->input, subj->pos, numdelims)); - append_inlines(last, new); - last = new; - if (first_close_delims == 1 && numdelims > 2) { - numdelims = 2; - } else if (first_close_delims == 2) { - numdelims = 1; - } else if (numdelims == 3) { - // If we opened with ***, we interpret it as ** followed by * - // giving us <strong><em> - numdelims = 1; - } - subj->pos += numdelims; - if (first_close) { - first_head->tag = first_close_delims == 1 ? INL_STRONG : INL_EMPH; - chunk_free(&first_head->content.literal); - first_head->content.inlines = - make_inlines(first_close_delims == 1 ? INL_EMPH : INL_STRONG, - first_head->next); - - il = first_head->next; - while (il->next && il->next != first_close) { - il = il->next; - } - il->next = NULL; - - first_head->content.inlines->next = first_close->next; - - il = first_head->content.inlines; - while (il->next && il->next != last) { - il = il->next; - } - il->next = NULL; - free_inlines(last); - - first_close->next = NULL; - free_inlines(first_close); - first_head->next = NULL; - goto done; - } else { - first_close = last; - first_close_delims = numdelims; - } - } else { - if (!parse_inline(subj, &last)) { - goto done; - } - } - } - break; - default: - goto done; + + if (can_close) + { + // walk the stack and find a matching opener, if there is one + istack = subj->emphasis_openers; + while (true) + { + if (istack == NULL) + goto cannotClose; + + if (istack->delim_char == c) + break; + + istack = istack->previous; + } + + // calculate the actual number of delimeters used from this closer + useDelims = istack->delim_count; + if (useDelims == 3) useDelims = numdelims == 3 ? 1 : numdelims; + else if (useDelims > numdelims) useDelims = 1; + + if (istack->delim_count == useDelims) + { + // the opener is completely used up - remove the stack entry and reuse the inline element + inl = istack->first_inline; + inl->tag = useDelims == 1 ? INL_EMPH : INL_STRONG; + chunk_free(&inl->content.literal); + inl->content.inlines = inl->next; + inl->next = NULL; + + // remove this opener and all later ones from stack: + free_openers(subj, istack->previous); + *last = inl; + } + else + { + // the opener will only partially be used - stack entry remains (truncated) and a new inline is added. + inl = istack->first_inline; + istack->delim_count -= useDelims; + inl->content.literal.len = istack->delim_count; + + emph = useDelims == 1 ? make_emph(inl->next) : make_strong(inl->next); + inl->next = emph; + + // remove all later openers from stack: + free_openers(subj, istack); + + *last = emph; + } + + // if the closer was not fully used, move back a char or two and try again. + if (useDelims < numdelims) + { + subj->pos = subj->pos - numdelims + useDelims; + return handle_strong_emph(subj, c, last); + } + + return NULL; // make_str(chunk_literal("")); + } + +cannotClose: + inl_text = make_str(chunk_dup(&subj->input, subj->pos - numdelims, numdelims)); + + if (can_open) + { + istack = (inline_stack*)malloc(sizeof(inline_stack)); + if (istack == NULL) { + return NULL; + } + istack->delim_count = numdelims; + istack->delim_char = c; + istack->first_inline = inl_text; + istack->previous = subj->emphasis_openers; + subj->emphasis_openers = istack; } -done: - return result; + return inl_text; } // Parse backslash-escape or just a backslash, returning an inline. @@ -445,9 +431,9 @@ static node_inl* handle_entity(subject* subj) advance(subj); len = houdini_unescape_ent(&ent, - subj->input.data + subj->pos, - subj->input.len - subj->pos - ); + subj->input.data + subj->pos, + subj->input.len - subj->pos + ); if (len == 0) return make_str(chunk_literal("&")); @@ -520,8 +506,8 @@ unsigned char *clean_title(chunk *title) // remove surrounding quotes if any: if ((first == '\'' && last == '\'') || - (first == '(' && last == ')') || - (first == '"' && last == '"')) { + (first == '(' && last == ')') || + (first == '"' && last == '"')) { houdini_unescape_html_f(&buf, title->data + 1, title->len - 2); } else { houdini_unescape_html_f(&buf, title->data, title->len); @@ -549,7 +535,7 @@ static node_inl* handle_pointy_brace(subject* subj) return make_autolink( make_str_with_entities(&contents), contents, 0 - ); + ); } // next try to match an email autolink @@ -559,9 +545,9 @@ static node_inl* handle_pointy_brace(subject* subj) subj->pos += matchlen; return make_autolink( - make_str_with_entities(&contents), - contents, 1 - ); + make_str_with_entities(&contents), + contents, 1 + ); } // finally, try to match an html tag @@ -602,33 +588,33 @@ static int link_label(subject* subj, chunk *raw_label) } advance(subj); // advance past [ - char c; + unsigned char c; while ((c = peek_char(subj)) && (c != ']' || nestlevel > 0)) { switch (c) { - case '`': - tmp = handle_backticks(subj); - free_inlines(tmp); - break; - case '<': - tmp = handle_pointy_brace(subj); - free_inlines(tmp); - break; - case '[': // nested [] - nestlevel++; - advance(subj); - break; - case ']': // nested [] - nestlevel--; - advance(subj); - break; - case '\\': - advance(subj); - if (ispunct(peek_char(subj))) { - advance(subj); - } - break; - default: + case '`': + tmp = handle_backticks(subj); + free_inlines(tmp); + break; + case '<': + tmp = handle_pointy_brace(subj); + free_inlines(tmp); + break; + case '[': // nested [] + nestlevel++; + advance(subj); + break; + case ']': // nested [] + nestlevel--; + advance(subj); + break; + case '\\': + advance(subj); + if (ispunct(peek_char(subj))) { advance(subj); + } + break; + default: + advance(subj); } } if (c == ']') { @@ -664,8 +650,8 @@ static node_inl* handle_left_bracket(subject* subj) if (found_label) { if (peek_char(subj) == '(' && - ((sps = scan_spacechars(&subj->input, subj->pos + 1)) > -1) && - ((n = scan_link_url(&subj->input, subj->pos + 1 + sps)) > -1)) { + ((sps = scan_spacechars(&subj->input, subj->pos + 1)) > -1) && + ((n = scan_link_url(&subj->input, subj->pos + 1 + sps)) > -1)) { // try to parse an explicit link: starturl = subj->pos + 1 + sps; // after ( @@ -691,8 +677,8 @@ static node_inl* handle_left_bracket(subject* subj) subj->pos = endlabel; lab = parse_chunk_inlines(&rawlabel, subj->refmap); result = append_inlines(make_str(chunk_literal("[")), - append_inlines(lab, - make_str(chunk_literal("]")))); + append_inlines(lab, + make_str(chunk_literal("]")))); return result; } } else { @@ -721,7 +707,7 @@ static node_inl* handle_left_bracket(subject* subj) subj->pos = endlabel; lab = parse_chunk_inlines(&rawlabel, subj->refmap); result = append_inlines(make_str(chunk_literal("[")), - append_inlines(lab, make_str(chunk_literal("]")))); + append_inlines(lab, make_str(chunk_literal("]")))); } return result; } @@ -743,8 +729,8 @@ static node_inl* handle_newline(subject *subj) advance(subj); } if (nlpos > 1 && - peek_at(subj, nlpos - 1) == ' ' && - peek_at(subj, nlpos - 2) == ' ') { + peek_at(subj, nlpos - 1) == ' ' && + peek_at(subj, nlpos - 2) == ' ') { return make_linebreak(); } else { return make_softbreak(); @@ -761,9 +747,22 @@ extern node_inl* parse_inlines_while(subject* subj, int (*f)(subject*)) { node_inl* result = NULL; node_inl** last = &result; + node_inl* first = NULL; while ((*f)(subj) && parse_inline(subj, last)) { + if (!first) { + first = *last; + } + } + + inline_stack* istack = subj->emphasis_openers; + inline_stack* temp; + while (istack != NULL) { + temp = istack->previous; + free(istack); + istack = temp; } - return result; + + return first; } node_inl *parse_chunk_inlines(chunk *chunk, reference_map *refmap) @@ -819,69 +818,62 @@ static int parse_inline(subject* subj, node_inl ** last) return 0; } switch(c){ - case '\n': - new = handle_newline(subj); - break; - case '`': - new = handle_backticks(subj); - break; - case '\\': - new = handle_backslash(subj); - break; - case '&': - new = handle_entity(subj); - break; - case '<': - new = handle_pointy_brace(subj); - break; - case '_': - if (subj->pos > 0) { - unsigned char prev = peek_at(subj, subj->pos - 1); - if (isalnum(prev) || prev == '_') { - new = make_str(chunk_literal("_")); - advance(subj); - break; - } - } - - new = handle_strong_emph(subj, '_'); - break; - case '*': - new = handle_strong_emph(subj, '*'); - break; - case '[': + case '\n': + new = handle_newline(subj); + break; + case '`': + new = handle_backticks(subj); + break; + case '\\': + new = handle_backslash(subj); + break; + case '&': + new = handle_entity(subj); + break; + case '<': + new = handle_pointy_brace(subj); + break; + case '_': + new = handle_strong_emph(subj, '_', last); + break; + case '*': + new = handle_strong_emph(subj, '*', last); + break; + case '[': + new = handle_left_bracket(subj); + break; + case '!': + advance(subj); + if (peek_char(subj) == '[') { new = handle_left_bracket(subj); - break; - case '!': - advance(subj); - if (peek_char(subj) == '[') { - new = handle_left_bracket(subj); - if (new != NULL && new->tag == INL_LINK) { - new->tag = INL_IMAGE; - } else { - new = append_inlines(make_str(chunk_literal("!")), new); - } + if (new != NULL && new->tag == INL_LINK) { + new->tag = INL_IMAGE; } else { - new = make_str(chunk_literal("!")); - } - break; - default: - endpos = subject_find_special_char(subj); - contents = chunk_dup(&subj->input, subj->pos, endpos - subj->pos); - subj->pos = endpos; - - // if we're at a newline, strip trailing spaces. - if (peek_char(subj) == '\n') { - chunk_rtrim(&contents); + new = append_inlines(make_str(chunk_literal("!")), new); } + } else { + new = make_str(chunk_literal("!")); + } + break; + default: + endpos = subject_find_special_char(subj); + contents = chunk_dup(&subj->input, subj->pos, endpos - subj->pos); + subj->pos = endpos; + + // if we're at a newline, strip trailing spaces. + if (peek_char(subj) == '\n') { + chunk_rtrim(&contents); + } - new = make_str(contents); + new = make_str(contents); } if (*last == NULL) { *last = new; - } else { + } else if (new) { append_inlines(*last, new); + *last = new; } + return 1; } @@ -897,8 +889,8 @@ void spnl(subject* subj) { bool seen_newline = false; while (peek_char(subj) == ' ' || - (!seen_newline && - (seen_newline = peek_char(subj) == '\n'))) { + (!seen_newline && + (seen_newline = peek_char(subj) == '\n'))) { advance(subj); } } @@ -965,4 +957,3 @@ int parse_reference_inline(strbuf *input, reference_map *refmap) reference_create(refmap, &lab, &url, &title); return subj.pos; } - @@ -38,7 +38,7 @@ int main(int argc, char *argv[]) printf(" - CommonMark converter (c) 2014 John MacFarlane\n"); exit(0); } else if ((strcmp(argv[i], "--help") == 0) || - (strcmp(argv[i], "-h") == 0)) { + (strcmp(argv[i], "-h") == 0)) { print_usage(); exit(0); } else if (strcmp(argv[i], "--ast") == 0) { @@ -61,7 +61,7 @@ int main(int argc, char *argv[]) if (fp == NULL) { fprintf(stderr, "Error opening file %s: %s\n", - argv[files[i]], strerror(errno)); + argv[files[i]], strerror(errno)); exit(1); } @@ -74,4 +74,3 @@ int main(int argc, char *argv[]) return 0; } - diff --git a/src/print.c b/src/print.c index 83f8daa..f3bd8e5 100644 --- a/src/print.c +++ b/src/print.c @@ -16,17 +16,17 @@ static void print_str(const unsigned char *s, int len) unsigned char c = s[i]; switch (c) { - case '\n': - printf("\\n"); - break; - case '"': - printf("\\\""); - break; - case '\\': - printf("\\\\"); - break; - default: - putchar((int)c); + case '\n': + printf("\\n"); + break; + case '"': + printf("\\\""); + break; + case '\\': + printf("\\\\"); + break; + default: + putchar((int)c); } } putchar('"'); @@ -116,13 +116,13 @@ static void print_blocks(node_block* b, int indent) data = &(b->as.list); if (data->list_type == ordered) { printf("list (type=ordered tight=%s start=%d delim=%s)\n", - (data->tight ? "true" : "false"), - data->start, - (data->delimiter == parens ? "parens" : "period")); + (data->tight ? "true" : "false"), + data->start, + (data->delimiter == parens ? "parens" : "period")); } else { printf("list (type=bullet tight=%s bullet_char=%c)\n", - (data->tight ? "true" : "false"), - data->bullet_char); + (data->tight ? "true" : "false"), + data->bullet_char); } print_blocks(b->children, indent + 2); break; @@ -148,7 +148,7 @@ static void print_blocks(node_block* b, int indent) break; case BLOCK_FENCED_CODE: printf("fenced_code length=%d info=", - b->as.code.fence_length); + b->as.code.fence_length); print_str(b->as.code.info.ptr, -1); putchar(' '); print_str(b->string_content.ptr, -1); diff --git a/src/references.c b/src/references.c index 0ae7961..6759c2c 100644 --- a/src/references.c +++ b/src/references.c @@ -60,7 +60,7 @@ static void add_reference(reference_map *map, reference* ref) while (t) { if (t->hash == ref->hash && - !strcmp((char *)t->label, (char *)ref->label)) { + !strcmp((char *)t->label, (char *)ref->label)) { reference_free(ref); return; } @@ -99,10 +99,10 @@ reference* reference_lookup(reference_map *map, chunk *label) reference *ref = NULL; unsigned char *norm; unsigned int hash; - + if (map == NULL) return NULL; - + norm = normalize_reference(label); if (norm == NULL) return NULL; @@ -112,7 +112,7 @@ reference* reference_lookup(reference_map *map, chunk *label) while (ref) { if (ref->hash == hash && - !strcmp((char *)ref->label, (char *)norm)) + !strcmp((char *)ref->label, (char *)norm)) break; ref = ref->next; } @@ -146,4 +146,3 @@ reference_map *reference_map_new(void) { return calloc(1, sizeof(reference_map)); } - @@ -56,7 +56,7 @@ struct ListData { struct FencedCodeData { int fence_length; int fence_offset; - char fence_char; + unsigned char fence_char; strbuf info; }; @@ -103,24 +103,24 @@ int utf8proc_iterate(const uint8_t *str, int str_len, int32_t *dst) return -1; switch (length) { - case 1: - uc = str[0]; - break; - case 2: - uc = ((str[0] & 0x1F) << 6) + (str[1] & 0x3F); - if (uc < 0x80) uc = -1; - break; - case 3: - uc = ((str[0] & 0x0F) << 12) + ((str[1] & 0x3F) << 6) - + (str[2] & 0x3F); - if (uc < 0x800 || (uc >= 0xD800 && uc < 0xE000) || - (uc >= 0xFDD0 && uc < 0xFDF0)) uc = -1; - break; - case 4: - uc = ((str[0] & 0x07) << 18) + ((str[1] & 0x3F) << 12) - + ((str[2] & 0x3F) << 6) + (str[3] & 0x3F); - if (uc < 0x10000 || uc >= 0x110000) uc = -1; - break; + case 1: + uc = str[0]; + break; + case 2: + uc = ((str[0] & 0x1F) << 6) + (str[1] & 0x3F); + if (uc < 0x80) uc = -1; + break; + case 3: + uc = ((str[0] & 0x0F) << 12) + ((str[1] & 0x3F) << 6) + + (str[2] & 0x3F); + if (uc < 0x800 || (uc >= 0xD800 && uc < 0xE000) || + (uc >= 0xFDD0 && uc < 0xFDF0)) uc = -1; + break; + case 4: + uc = ((str[0] & 0x07) << 18) + ((str[1] & 0x3F) << 12) + + ((str[2] & 0x3F) << 6) + (str[3] & 0x3F); + if (uc < 0x10000 || uc >= 0x110000) uc = -1; + break; } if (uc < 0 || ((uc & 0xFFFF) >= 0xFFFE)) @@ -173,7 +173,7 @@ void utf8proc_case_fold(strbuf *dest, const uint8_t *str, int len) { int32_t c; -#define bufpush(x) \ +#define bufpush(x) \ utf8proc_encode_char(x, dest) while (len > 0) { @@ -190,4 +190,3 @@ void utf8proc_case_fold(strbuf *dest, const uint8_t *str, int len) len -= char_len; } } - |