diff options
author | John MacFarlane <jgm@berkeley.edu> | 2017-11-05 12:48:26 -0500 |
---|---|---|
committer | GitHub <noreply@github.com> | 2017-11-05 12:48:26 -0500 |
commit | b40ecdcd459bff13ecdb0ab586abf22fb223490f (patch) | |
tree | 0177899c8713b2bf13c437c83dabd54032463d6e /src | |
parent | 5da792fc3714f66a88aabb5d13cb0eed674cb6c5 (diff) | |
parent | 1326fd0d8d945b1eb33c5c5d2f536c6fda0201d1 (diff) |
Merge pull request #228 from github/upstream/inline-sourcepos
Add sourcepos info for inlines
Diffstat (limited to 'src')
-rw-r--r-- | src/blocks.c | 1 | ||||
-rw-r--r-- | src/inlines.c | 171 | ||||
-rw-r--r-- | src/iterator.c | 1 | ||||
-rw-r--r-- | src/node.h | 1 |
4 files changed, 124 insertions, 50 deletions
diff --git a/src/blocks.c b/src/blocks.c index 3e810bc..7f58ffd 100644 --- a/src/blocks.c +++ b/src/blocks.c @@ -904,6 +904,7 @@ static void open_new_blocks(cmark_parser *parser, cmark_node **container, (*container)->as.heading.level = level; (*container)->as.heading.setext = false; + (*container)->internal_offset = matched; } else if (!indented && (matched = scan_open_code_fence( input, parser->first_nonspace))) { diff --git a/src/inlines.c b/src/inlines.c index c445f2f..3bade11 100644 --- a/src/inlines.c +++ b/src/inlines.c @@ -22,9 +22,9 @@ static const char *LEFTSINGLEQUOTE = "\xE2\x80\x98"; static const char *RIGHTSINGLEQUOTE = "\xE2\x80\x99"; // Macros for creating various kinds of simple. -#define make_str(mem, s) make_literal(mem, CMARK_NODE_TEXT, s) -#define make_code(mem, s) make_literal(mem, CMARK_NODE_CODE, s) -#define make_raw_html(mem, s) make_literal(mem, CMARK_NODE_HTML_INLINE, s) +#define make_str(subj, sc, ec, s) make_literal(subj, CMARK_NODE_TEXT, sc, ec, s) +#define make_code(subj, sc, ec, s) make_literal(subj, CMARK_NODE_CODE, sc, ec, s) +#define make_raw_html(subj, sc, ec, s) make_literal(subj, CMARK_NODE_HTML_INLINE, sc, ec, s) #define make_linebreak(mem) make_simple(mem, CMARK_NODE_LINEBREAK) #define make_softbreak(mem) make_simple(mem, CMARK_NODE_SOFTBREAK) #define make_emph(mem) make_simple(mem, CMARK_NODE_EMPH) @@ -55,7 +55,10 @@ typedef struct bracket { typedef struct { cmark_mem *mem; cmark_chunk input; + int line; bufsize_t pos; + int block_offset; + int column_offset; cmark_reference_map *refmap; delimiter *last_delim; bracket *last_bracket; @@ -72,17 +75,22 @@ static delimiter *S_insert_emph(subject *subj, delimiter *opener, static int parse_inline(subject *subj, cmark_node *parent, int options); -static void subject_from_buf(cmark_mem *mem, subject *e, cmark_chunk *chunk, - cmark_reference_map *refmap); +static void subject_from_buf(cmark_mem *mem, int line_number, int block_offset, subject *e, + cmark_chunk *chunk, cmark_reference_map *refmap); static bufsize_t subject_find_special_char(subject *subj, int options); // Create an inline with a literal string value. -static CMARK_INLINE cmark_node *make_literal(cmark_mem *mem, cmark_node_type t, +static CMARK_INLINE cmark_node *make_literal(subject *subj, cmark_node_type t, + int start_column, int end_column, cmark_chunk s) { - cmark_node *e = (cmark_node *)mem->calloc(1, sizeof(*e)); - cmark_strbuf_init(mem, &e->content, 0); - e->type = t; + cmark_node *e = (cmark_node *)subj->mem->calloc(1, sizeof(*e)); + cmark_strbuf_init(subj->mem, &e->content, 0); + e->type = (uint16_t)t; e->as.literal = s; + e->start_line = e->end_line = subj->line; + // columns are 1 based. + e->start_column = start_column + 1 + subj->column_offset + subj->block_offset; + e->end_column = end_column + 1 + subj->column_offset + subj->block_offset; return e; } @@ -95,14 +103,15 @@ static CMARK_INLINE cmark_node *make_simple(cmark_mem *mem, cmark_node_type t) { } // Like make_str, but parses entities. -static cmark_node *make_str_with_entities(cmark_mem *mem, +static cmark_node *make_str_with_entities(subject *subj, + int start_column, int end_column, cmark_chunk *content) { - cmark_strbuf unescaped = CMARK_BUF_INIT(mem); + cmark_strbuf unescaped = CMARK_BUF_INIT(subj->mem); if (houdini_unescape_html(&unescaped, content->data, content->len)) { - return make_str(mem, cmark_chunk_buf_detach(&unescaped)); + return make_str(subj, start_column, end_column, cmark_chunk_buf_detach(&unescaped)); } else { - return make_str(mem, *content); + return make_str(subj, start_column, end_column, *content); } } @@ -140,21 +149,28 @@ static cmark_chunk cmark_clean_autolink(cmark_mem *mem, cmark_chunk *url, return cmark_chunk_buf_detach(&buf); } -static CMARK_INLINE cmark_node *make_autolink(cmark_mem *mem, cmark_chunk url, - int is_email) { - cmark_node *link = make_simple(mem, CMARK_NODE_LINK); - link->as.link.url = cmark_clean_autolink(mem, &url, is_email); +static CMARK_INLINE cmark_node *make_autolink(subject *subj, + int start_column, int end_column, + cmark_chunk url, int is_email) { + cmark_node *link = make_simple(subj->mem, CMARK_NODE_LINK); + link->as.link.url = cmark_clean_autolink(subj->mem, &url, is_email); link->as.link.title = cmark_chunk_literal(""); - cmark_node_append_child(link, make_str_with_entities(mem, &url)); + link->start_line = link->end_line = subj->line; + link->start_column = start_column + 1; + link->end_column = end_column + 1; + cmark_node_append_child(link, make_str_with_entities(subj, start_column + 1, end_column - 1, &url)); return link; } -static void subject_from_buf(cmark_mem *mem, subject *e, cmark_chunk *chunk, - cmark_reference_map *refmap) { +static void subject_from_buf(cmark_mem *mem, int line_number, int block_offset, subject *e, + cmark_chunk *chunk, cmark_reference_map *refmap) { int i; e->mem = mem; e->input = *chunk; + e->line = line_number; e->pos = 0; + e->block_offset = block_offset; + e->column_offset = 0; e->refmap = refmap; e->last_delim = NULL; e->last_bracket = NULL; @@ -221,6 +237,47 @@ static CMARK_INLINE cmark_chunk take_while(subject *subj, int (*f)(int)) { return cmark_chunk_dup(&subj->input, startpos, len); } +// Return the number of newlines in a given span of text in a subject. If +// the number is greater than zero, also return the number of characters +// between the last newline and the end of the span in `since_newline`. +static int count_newlines(subject *subj, bufsize_t from, bufsize_t len, int *since_newline) { + int nls = 0; + int since_nl = 0; + + while (len--) { + if (subj->input.data[from++] == '\n') { + ++nls; + since_nl = 0; + } else { + ++since_nl; + } + } + + if (!nls) + return 0; + + *since_newline = since_nl; + return nls; +} + +// Adjust `node`'s `end_line`, `end_column`, and `subj`'s `line` and +// `column_offset` according to the number of newlines in a just-matched span +// of text in `subj`. +static void adjust_subj_node_newlines(subject *subj, cmark_node *node, int matchlen, int extra, int options) { + if (!(options & CMARK_OPT_SOURCEPOS)) { + return; + } + + int since_newline; + int newlines = count_newlines(subj, subj->pos - matchlen - extra, matchlen, &since_newline); + if (newlines) { + subj->line += newlines; + node->end_line += newlines; + node->end_column = since_newline; + subj->column_offset = -subj->pos + since_newline + extra; + } +} + // Try to process a backtick code span that began with a // span of ticks of length openticklength length (already // parsed). Return 0 if you don't find matching closing @@ -268,14 +325,14 @@ static bufsize_t scan_to_closing_backticks(subject *subj, // Parse backtick code section or raw backticks, return an inline. // Assumes that the subject has a backtick at the current position. -static cmark_node *handle_backticks(subject *subj) { +static cmark_node *handle_backticks(subject *subj, int options) { cmark_chunk openticks = take_while(subj, isbacktick); bufsize_t startpos = subj->pos; bufsize_t endpos = scan_to_closing_backticks(subj, openticks.len); if (endpos == 0) { // not found subj->pos = startpos; // rewind - return make_str(subj->mem, openticks); + return make_str(subj, subj->pos, subj->pos, openticks); } else { cmark_strbuf buf = CMARK_BUF_INIT(subj->mem); @@ -284,7 +341,9 @@ static cmark_node *handle_backticks(subject *subj) { cmark_strbuf_trim(&buf); cmark_strbuf_normalize_whitespace(&buf); - return make_code(subj->mem, cmark_chunk_buf_detach(&buf)); + cmark_node *node = make_code(subj, startpos, endpos - openticks.len - 1, cmark_chunk_buf_detach(&buf)); + adjust_subj_node_newlines(subj, node, endpos - startpos, openticks.len, options); + return node; } } @@ -442,7 +501,7 @@ static cmark_node *handle_delim(subject *subj, unsigned char c, bool smart) { contents = cmark_chunk_dup(&subj->input, subj->pos - numdelims, numdelims); } - inl_text = make_str(subj->mem, contents); + inl_text = make_str(subj, subj->pos - numdelims, subj->pos - 1, contents); if ((can_open || can_close) && (!(c == '\'' || c == '"') || smart)) { push_delimiter(subj, c, can_open, can_close, inl_text); @@ -458,7 +517,7 @@ static cmark_node *handle_hyphen(subject *subj, bool smart) { advance(subj); if (!smart || peek_char(subj) != '-') { - return make_str(subj->mem, cmark_chunk_literal("-")); + return make_str(subj, subj->pos - 1, subj->pos - 1, cmark_chunk_literal("-")); } while (smart && peek_char(subj) == '-') { @@ -491,7 +550,7 @@ static cmark_node *handle_hyphen(subject *subj, bool smart) { cmark_strbuf_puts(&buf, ENDASH); } - return make_str(subj->mem, cmark_chunk_buf_detach(&buf)); + return make_str(subj, startpos, subj->pos - 1, cmark_chunk_buf_detach(&buf)); } // Assumes we have a period at the current position. @@ -501,12 +560,12 @@ static cmark_node *handle_period(subject *subj, bool smart) { advance(subj); if (peek_char(subj) == '.') { advance(subj); - return make_str(subj->mem, cmark_chunk_literal(ELLIPSES)); + return make_str(subj, subj->pos - 3, subj->pos - 1, cmark_chunk_literal(ELLIPSES)); } else { - return make_str(subj->mem, cmark_chunk_literal("..")); + return make_str(subj, subj->pos - 2, subj->pos - 1, cmark_chunk_literal("..")); } } else { - return make_str(subj->mem, cmark_chunk_literal(".")); + return make_str(subj, subj->pos - 1, subj->pos - 1, cmark_chunk_literal(".")); } } @@ -642,6 +701,10 @@ static delimiter *S_insert_emph(subject *subj, delimiter *opener, } cmark_node_insert_after(opener_inl, emph); + emph->start_line = emph->end_line = subj->line; + emph->start_column = opener_inl->start_column + subj->column_offset; + emph->end_column = closer_inl->end_column + subj->column_offset; + // if opener has 0 characters, remove it and its associated inline if (opener_num_chars == 0) { cmark_node_free(opener_inl); @@ -668,11 +731,11 @@ static cmark_node *handle_backslash(subject *subj) { if (cmark_ispunct( nextchar)) { // only ascii symbols and newline can be escaped advance(subj); - return make_str(subj->mem, cmark_chunk_dup(&subj->input, subj->pos - 1, 1)); + return make_str(subj, subj->pos - 2, subj->pos - 1, cmark_chunk_dup(&subj->input, subj->pos - 1, 1)); } else if (!is_eof(subj) && skip_line_end(subj)) { return make_linebreak(subj->mem); } else { - return make_str(subj->mem, cmark_chunk_literal("\\")); + return make_str(subj, subj->pos - 1, subj->pos - 1, cmark_chunk_literal("\\")); } } @@ -688,10 +751,10 @@ static cmark_node *handle_entity(subject *subj) { subj->input.len - subj->pos); if (len == 0) - return make_str(subj->mem, cmark_chunk_literal("&")); + return make_str(subj, subj->pos - 1, subj->pos - 1, cmark_chunk_literal("&")); subj->pos += len; - return make_str(subj->mem, cmark_chunk_buf_detach(&ent)); + return make_str(subj, subj->pos - 1 - len, subj->pos - 1, cmark_chunk_buf_detach(&ent)); } // Clean a URL: remove surrounding whitespace, and remove \ that escape @@ -738,7 +801,7 @@ cmark_chunk cmark_clean_title(cmark_mem *mem, cmark_chunk *title) { // Parse an autolink or HTML tag. // Assumes the subject has a '<' character at the current position. -static cmark_node *handle_pointy_brace(subject *subj) { +static cmark_node *handle_pointy_brace(subject *subj, int options) { bufsize_t matchlen = 0; cmark_chunk contents; @@ -750,7 +813,7 @@ static cmark_node *handle_pointy_brace(subject *subj) { contents = cmark_chunk_dup(&subj->input, subj->pos, matchlen - 1); subj->pos += matchlen; - return make_autolink(subj->mem, contents, 0); + return make_autolink(subj, subj->pos - 1 - matchlen, subj->pos - 1, contents, 0); } // next try to match an email autolink @@ -759,7 +822,7 @@ static cmark_node *handle_pointy_brace(subject *subj) { contents = cmark_chunk_dup(&subj->input, subj->pos, matchlen - 1); subj->pos += matchlen; - return make_autolink(subj->mem, contents, 1); + return make_autolink(subj, subj->pos - 1 - matchlen, subj->pos - 1, contents, 1); } // finally, try to match an html tag @@ -767,11 +830,13 @@ static cmark_node *handle_pointy_brace(subject *subj) { if (matchlen > 0) { contents = cmark_chunk_dup(&subj->input, subj->pos - 1, matchlen + 1); subj->pos += matchlen; - return make_raw_html(subj->mem, contents); + cmark_node *node = make_raw_html(subj, subj->pos - matchlen - 1, subj->pos - 1, contents); + adjust_subj_node_newlines(subj, node, matchlen, 1, options); + return node; } // if nothing matches, just return the opening <: - return make_str(subj->mem, cmark_chunk_literal("<")); + return make_str(subj, subj->pos - 1, subj->pos - 1, cmark_chunk_literal("<")); } // Parse a link label. Returns 1 if successful. @@ -907,13 +972,13 @@ static cmark_node *handle_close_bracket(subject *subj) { opener = subj->last_bracket; if (opener == NULL) { - return make_str(subj->mem, cmark_chunk_literal("]")); + return make_str(subj, subj->pos - 1, subj->pos - 1, cmark_chunk_literal("]")); } if (!opener->active) { // take delimiter off stack pop_bracket(subj); - return make_str(subj->mem, cmark_chunk_literal("]")); + return make_str(subj, subj->pos - 1, subj->pos - 1, cmark_chunk_literal("]")); } // If we got here, we matched a potential link/image text. @@ -990,12 +1055,15 @@ noMatch: // If we fall through to here, it means we didn't match a link: pop_bracket(subj); // remove this opener from delimiter list subj->pos = initial_pos; - return make_str(subj->mem, cmark_chunk_literal("]")); + return make_str(subj, subj->pos - 1, subj->pos - 1, cmark_chunk_literal("]")); match: inl = make_simple(subj->mem, is_image ? CMARK_NODE_IMAGE : CMARK_NODE_LINK); inl->as.link.url = url; inl->as.link.title = title; + inl->start_line = inl->end_line = subj->line; + inl->start_column = opener->inl_text->start_column; + inl->end_column = subj->pos + subj->column_offset + subj->block_offset; cmark_node_insert_before(opener->inl_text, inl); // Add link text: tmp = opener->inl_text->next; @@ -1042,6 +1110,8 @@ static cmark_node *handle_newline(subject *subj) { if (peek_at(subj, subj->pos) == '\n') { advance(subj); } + ++subj->line; + subj->column_offset = -subj->pos; // skip spaces at beginning of line skip_spaces(subj); if (nlpos > 1 && peek_at(subj, nlpos - 1) == ' ' && @@ -1101,7 +1171,7 @@ static int parse_inline(subject *subj, cmark_node *parent, int options) { cmark_node *new_inl = NULL; cmark_chunk contents; unsigned char c; - bufsize_t endpos; + bufsize_t startpos, endpos; c = peek_char(subj); if (c == 0) { return 0; @@ -1112,7 +1182,7 @@ static int parse_inline(subject *subj, cmark_node *parent, int options) { new_inl = handle_newline(subj); break; case '`': - new_inl = handle_backticks(subj); + new_inl = handle_backticks(subj, options); break; case '\\': new_inl = handle_backslash(subj); @@ -1121,7 +1191,7 @@ static int parse_inline(subject *subj, cmark_node *parent, int options) { new_inl = handle_entity(subj); break; case '<': - new_inl = handle_pointy_brace(subj); + new_inl = handle_pointy_brace(subj, options); break; case '*': case '_': @@ -1137,7 +1207,7 @@ static int parse_inline(subject *subj, cmark_node *parent, int options) { break; case '[': advance(subj); - new_inl = make_str(subj->mem, cmark_chunk_literal("[")); + new_inl = make_str(subj, subj->pos - 1, subj->pos - 1, cmark_chunk_literal("[")); push_bracket(subj, false, new_inl); break; case ']': @@ -1147,15 +1217,16 @@ static int parse_inline(subject *subj, cmark_node *parent, int options) { advance(subj); if (peek_char(subj) == '[') { advance(subj); - new_inl = make_str(subj->mem, cmark_chunk_literal("![")); + new_inl = make_str(subj, subj->pos - 2, subj->pos - 1, cmark_chunk_literal("![")); push_bracket(subj, true, new_inl); } else { - new_inl = make_str(subj->mem, cmark_chunk_literal("!")); + new_inl = make_str(subj, subj->pos - 1, subj->pos - 1, cmark_chunk_literal("!")); } break; default: endpos = subject_find_special_char(subj, options); contents = cmark_chunk_dup(&subj->input, subj->pos, endpos - subj->pos); + startpos = subj->pos; subj->pos = endpos; // if we're at a newline, strip trailing spaces. @@ -1163,7 +1234,7 @@ static int parse_inline(subject *subj, cmark_node *parent, int options) { cmark_chunk_rtrim(&contents); } - new_inl = make_str(subj->mem, contents); + new_inl = make_str(subj, startpos, endpos - 1, contents); } if (new_inl != NULL) { cmark_node_append_child(parent, new_inl); @@ -1177,7 +1248,7 @@ extern void cmark_parse_inlines(cmark_mem *mem, cmark_node *parent, cmark_reference_map *refmap, int options) { subject subj; cmark_chunk content = {parent->content.ptr, parent->content.size, 0}; - subject_from_buf(mem, &subj, &content, refmap); + subject_from_buf(mem, parent->start_line, parent->start_column - 1 + parent->internal_offset, &subj, &content, refmap); cmark_chunk_rtrim(&subj.input); while (!is_eof(&subj) && parse_inline(&subj, parent, options)) @@ -1216,7 +1287,7 @@ bufsize_t cmark_parse_reference_inline(cmark_mem *mem, cmark_chunk *input, bufsize_t matchlen = 0; bufsize_t beforetitle; - subject_from_buf(mem, &subj, input, NULL); + subject_from_buf(mem, -1, 0, &subj, input, NULL); // parse label: if (!link_label(&subj, &lab) || lab.len == 0) diff --git a/src/iterator.c b/src/iterator.c index 24423a2..f5cd802 100644 --- a/src/iterator.c +++ b/src/iterator.c @@ -106,6 +106,7 @@ void cmark_consolidate_text_nodes(cmark_node *root) { while (tmp && tmp->type == CMARK_NODE_TEXT) { cmark_iter_next(iter); // advance pointer cmark_strbuf_put(&buf, tmp->as.literal.data, tmp->as.literal.len); + cur->end_column = tmp->end_column; next = tmp->next; cmark_node_free(tmp); tmp = next; @@ -66,6 +66,7 @@ struct cmark_node { int start_column; int end_line; int end_column; + int internal_offset; uint16_t type; uint16_t flags; |