summaryrefslogtreecommitdiff
path: root/src
diff options
context:
space:
mode:
authorJohn MacFarlane <jgm@berkeley.edu>2017-11-05 12:48:26 -0500
committerGitHub <noreply@github.com>2017-11-05 12:48:26 -0500
commitb40ecdcd459bff13ecdb0ab586abf22fb223490f (patch)
tree0177899c8713b2bf13c437c83dabd54032463d6e /src
parent5da792fc3714f66a88aabb5d13cb0eed674cb6c5 (diff)
parent1326fd0d8d945b1eb33c5c5d2f536c6fda0201d1 (diff)
Merge pull request #228 from github/upstream/inline-sourcepos
Add sourcepos info for inlines
Diffstat (limited to 'src')
-rw-r--r--src/blocks.c1
-rw-r--r--src/inlines.c171
-rw-r--r--src/iterator.c1
-rw-r--r--src/node.h1
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;
diff --git a/src/node.h b/src/node.h
index 65d857f..13901ba 100644
--- a/src/node.h
+++ b/src/node.h
@@ -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;