1 files changed, 144 insertions, 72 deletions

diff --git a/src/inlines.c b/src/inlines.c
index 2d7f385..d0ab253 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_strbuf *buffer,
-                             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);
   }
 }
 
@@ -140,23 +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_strbuf *buffer,
-                             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.data = buffer->ptr;
-  e->input.len = buffer->size;
-  e->input.alloc = 0;
+  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;
@@ -223,6 +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
@@ -270,14 +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);
 
@@ -286,7 +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;
   }
 }
 
@@ -444,7 +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);
@@ -460,7 +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) == '-') {
@@ -493,7 +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.
@@ -503,12 +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("."));
   }
 }
 
@@ -644,6 +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);
@@ -670,11 +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("\\"));
   }
 }
 
@@ -690,10 +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
@@ -708,7 +769,7 @@ cmark_chunk cmark_clean_url(cmark_mem *mem, cmark_chunk *url) {
     return result;
   }
 
-  houdini_unescape_html_f(&buf, url->data, url->len);
+    houdini_unescape_html_f(&buf, url->data, url->len);
 
   cmark_strbuf_unescape(&buf);
   return cmark_chunk_buf_detach(&buf);
@@ -740,7 +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;
 
@@ -752,7 +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
@@ -761,7 +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
@@ -769,11 +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.
@@ -827,24 +890,26 @@ static bufsize_t manual_scan_link_url_2(cmark_chunk *input, bufsize_t offset,
   bufsize_t i = offset;
   size_t nb_p = 0;
 
-  while (i < input->len) {
-    if (input->data[i] == '\\' &&
-        i + 1 < input-> len &&
-        cmark_ispunct(input->data[i+1]))
-      i += 2;
-    else if (input->data[i] == '(') {
-      ++nb_p;
-      ++i;
-    } else if (input->data[i] == ')') {
-      if (nb_p == 0)
+    while (i < input->len) {
+      if (input->data[i] == '\\' &&
+	  i + 1 < input-> len &&
+          cmark_ispunct(input->data[i+1]))
+        i += 2;
+      else if (input->data[i] == '(') {
+        ++nb_p;
+        ++i;
+        if (nb_p > 32)
+          return -1;
+      } else if (input->data[i] == ')') {
+        if (nb_p == 0)
+          break;
+        --nb_p;
+        ++i;
+      } else if (cmark_isspace(input->data[i]))
         break;
-      --nb_p;
-      ++i;
-    } else if (cmark_isspace(input->data[i]))
-      break;
-    else
-      ++i;
-  }
+      else
+        ++i;
+    }
 
   if (i >= input->len)
     return -1;
@@ -909,13 +974,13 @@ 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.
@@ -992,12 +1057,15 @@ 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;
@@ -1044,6 +1112,8 @@ 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) == ' ' &&
@@ -1103,7 +1173,7 @@ 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;
@@ -1114,7 +1184,7 @@ 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);
@@ -1123,7 +1193,7 @@ 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 '_':
@@ -1139,7 +1209,7 @@ 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 ']':
@@ -1149,15 +1219,16 @@ 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.
@@ -1165,7 +1236,7 @@ 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);
@@ -1178,7 +1249,8 @@ static int parse_inline(subject *subj, cmark_node *parent, int options) {
 extern void cmark_parse_inlines(cmark_mem *mem, cmark_node *parent,
                                 cmark_reference_map *refmap, int options) {
   subject subj;
-  subject_from_buf(mem, &subj, &parent->content, refmap);
+  cmark_chunk content = {parent->content.ptr, parent->content.size, 0};
+  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))
@@ -1206,7 +1278,7 @@ static void spnl(subject *subj) {
 // Modify refmap if a reference is encountered.
 // Return 0 if no reference found, otherwise position of subject
 // after reference is parsed.
-bufsize_t cmark_parse_reference_inline(cmark_mem *mem, cmark_strbuf *input,
+bufsize_t cmark_parse_reference_inline(cmark_mem *mem, cmark_chunk *input,
                                        cmark_reference_map *refmap) {
   subject subj;
 
@@ -1217,7 +1289,7 @@ bufsize_t cmark_parse_reference_inline(cmark_mem *mem, cmark_strbuf *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)