diff options
| -rw-r--r-- | src/blocks.c | 199 | ||||
| -rw-r--r-- | src/buffer.c | 11 | ||||
| -rw-r--r-- | src/inlines.c | 219 | ||||
| -rw-r--r-- | src/main.c | 5 | ||||
| -rw-r--r-- | src/print.c | 34 | ||||
| -rw-r--r-- | src/references.c | 5 | ||||
| -rw-r--r-- | src/utf8.c | 39 |
7 files changed, 253 insertions, 259 deletions
diff --git a/src/blocks.c b/src/blocks.c index 5b38116..c0c7e23 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) @@ -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; @@ -355,9 +355,9 @@ 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) @@ -486,7 +486,7 @@ 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) { @@ -506,7 +506,7 @@ 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; @@ -550,7 +550,7 @@ 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) == ' ') @@ -603,17 +603,17 @@ 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); @@ -646,16 +646,16 @@ 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); @@ -684,11 +684,11 @@ 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) { @@ -697,10 +697,10 @@ 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); @@ -721,7 +721,7 @@ 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; @@ -767,4 +767,3 @@ 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 e0c1441..1eb5056 100644 --- a/src/inlines.c +++ b/src/inlines.c @@ -116,26 +116,26 @@ 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); @@ -405,9 +405,9 @@ 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("&")); @@ -480,8 +480,8 @@ 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); @@ -509,7 +509,7 @@ 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 @@ -519,9 +519,9 @@ 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 @@ -565,30 +565,30 @@ static int link_label(subject* subj, chunk *raw_label) 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 == ']') { @@ -624,8 +624,8 @@ 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 ( @@ -651,8 +651,8 @@ 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 { @@ -681,7 +681,7 @@ 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; } @@ -703,8 +703,8 @@ 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(); @@ -789,67 +789,67 @@ static int parse_inline(subject* subj, node_inl ** first, 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 '_': - new = handle_strong_emph(subj, '_', last); - break; - case '*': - new = handle_strong_emph(subj, '*', last); - 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 (*first == NULL) { - *first = new; + *first = new; *last = new; } else { append_inlines(*first, new); } - + while (new->next) { new = new->next; } - *last = new; - + *last = new; + return 1; } @@ -865,8 +865,8 @@ 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); } } @@ -933,4 +933,3 @@ 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 3e54b48..975bf81 100644 --- a/src/references.c +++ b/src/references.c @@ -55,7 +55,7 @@ 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; } @@ -105,7 +105,7 @@ 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; } @@ -138,4 +138,3 @@ reference_map *reference_map_new(void) memset(map, 0x0, sizeof(reference_map)); return map; } - @@ -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; } } - |