diff options
| -rw-r--r-- | man/man3/cmark.3 | 16 | ||||
| -rw-r--r-- | src/cmark.h | 6 | ||||
| -rw-r--r-- | src/inlines.c | 5 | ||||
| -rw-r--r-- | src/parser.h | 1 | ||||
| -rw-r--r-- | test/regression.txt | 31 | ||||
| -rw-r--r-- | test/spec.txt | 88 |
6 files changed, 114 insertions, 33 deletions
diff --git a/man/man3/cmark.3 b/man/man3/cmark.3 index 8e4b4c7..65ab6d6 100644 --- a/man/man3/cmark.3 +++ b/man/man3/cmark.3 @@ -1,4 +1,4 @@ -.TH cmark 3 "March 17, 2019" "LOCAL" "Library Functions Manual" +.TH cmark 3 "March 19, 2019" "LOCAL" "Library Functions Manual" .SH NAME .PP @@ -721,6 +721,20 @@ Render \f[C]softbreak\f[] elements as hard line breaks. .nf \fC .RS 0n +#define CMARK_OPT_SAFE (1 << 3) +.RE +\f[] +.fi + +.PP +\f[C]CMARK_OPT_SAFE\f[] is defined here for API compatibility, but it no +longer has any effect. "Safe" mode is now the default: set +\f[C]CMARK_OPT_UNSAFE\f[] to disable it. + +.PP +.nf +\fC +.RS 0n #define CMARK_OPT_UNSAFE (1 << 17) .RE \f[] diff --git a/src/cmark.h b/src/cmark.h index ad9d4c4..102aa6f 100644 --- a/src/cmark.h +++ b/src/cmark.h @@ -552,6 +552,12 @@ char *cmark_render_latex(cmark_node *root, int options, int width); */ #define CMARK_OPT_HARDBREAKS (1 << 2) +/** `CMARK_OPT_SAFE` is defined here for API compatibility, + but it no longer has any effect. "Safe" mode is now the default: + set `CMARK_OPT_UNSAFE` to disable it. + */ +#define CMARK_OPT_SAFE (1 << 3) + /** Render raw HTML and unsafe links (`javascript:`, `vbscript:`, * `file:`, and `data:`, except for `image/png`, `image/gif`, * `image/jpeg`, or `image/webp` mime types). By default, diff --git a/src/inlines.c b/src/inlines.c index dc899dc..6f93fd4 100644 --- a/src/inlines.c +++ b/src/inlines.c @@ -642,7 +642,8 @@ static void process_emphasis(subject *subj, delimiter *stack_bottom) { // interior closer of size 2 can't match opener of size 1 // or of size 1 can't match 2 if (!(closer->can_open || opener->can_close) || - ((opener->length + closer->length) % 3) != 0) { + closer->length % 3 == 0 || + (opener->length + closer->length) % 3 != 0) { opener_found = true; break; } @@ -966,7 +967,7 @@ static bufsize_t manual_scan_link_url(cmark_chunk *input, bufsize_t offset, } else if (input->data[i] == '\\') i += 2; else if (input->data[i] == '\n' || input->data[i] == '<') - return manual_scan_link_url_2(input, offset, output); + return -1; else ++i; } diff --git a/src/parser.h b/src/parser.h index 7f8ac9d..39e2327 100644 --- a/src/parser.h +++ b/src/parser.h @@ -2,6 +2,7 @@ #define CMARK_AST_H #include <stdio.h> +#include "references.h" #include "node.h" #include "buffer.h" #include "memory.h" diff --git a/test/regression.txt b/test/regression.txt index 4ec2c25..62b1e7e 100644 --- a/test/regression.txt +++ b/test/regression.txt @@ -81,7 +81,8 @@ Issue #193 - unescaped left angle brackets in link destination [a]: <te<st> . -<p><a href="%3Cte%3Cst%3E">a</a></p> +<p>[a]</p> +<p>[a]: <te<st></p> ```````````````````````````````` Issue #192 - escaped spaces in link destination @@ -118,8 +119,9 @@ Issue #530 - link parsing corner cases ) . <p>[a](\ b)</p> -<p><a href="%3C%3Cb">a</a></p> -<p><a href="%3Cb">a</a></p> +<p>[a](<<b)</p> +<p>[a](<b +)</p> ```````````````````````````````` Issue commonmark#526 - unescaped ( in link title @@ -129,3 +131,26 @@ Issue commonmark#526 - unescaped ( in link title . <p>[link](url ((title))</p> ```````````````````````````````` + +Issue commonamrk#517 - script, pre, style close tag without +opener. + +```````````````````````````````` example +</script> + +</pre> + +</style> +. +</script> +</pre> +</style> +```````````````````````````````` + +Issue #289. + +```````````````````````````````` example +[a](<b) c> +. +<p>[a](<b) c></p> +```````````````````````````````` diff --git a/test/spec.txt b/test/spec.txt index 91551e5..4162938 100644 --- a/test/spec.txt +++ b/test/spec.txt @@ -328,8 +328,10 @@ that is not a [whitespace character]. An [ASCII punctuation character](@) is `!`, `"`, `#`, `$`, `%`, `&`, `'`, `(`, `)`, -`*`, `+`, `,`, `-`, `.`, `/`, `:`, `;`, `<`, `=`, `>`, `?`, `@`, -`[`, `\`, `]`, `^`, `_`, `` ` ``, `{`, `|`, `}`, or `~`. +`*`, `+`, `,`, `-`, `.`, `/` (U+0021–2F), +`:`, `;`, `<`, `=`, `>`, `?`, `@` (U+003A–0040), +`[`, `\`, `]`, `^`, `_`, `` ` `` (U+005B–0060), +`{`, `|`, `}`, or `~` (U+007B–007E). A [punctuation character](@) is an [ASCII punctuation character] or anything in @@ -1922,9 +1924,11 @@ bar An [info string] can be provided after the opening code fence. -Opening and closing spaces will be stripped, and the first word, prefixed -with `language-`, is used as the value for the `class` attribute of the -`code` element within the enclosing `pre` element. +Although this spec doesn't mandate any particular treatment of +the info string, the first word is typically used to specify +the language of the code block. In HTML output, the language is +normally indicated by adding a class to the `code` element consisting +of `language-` followed by the language name. ```````````````````````````````` example ```ruby @@ -2003,15 +2007,15 @@ Closing code fences cannot have [info strings]: An [HTML block](@) is a group of lines that is treated as raw HTML (and will not be escaped in HTML output). -There are seven kinds of [HTML block], which can be defined -by their start and end conditions. The block begins with a line that -meets a [start condition](@) (after up to three spaces -optional indentation). It ends with the first subsequent line that -meets a matching [end condition](@), or the last line of -the document or other [container block](#container-blocks)), if no -line is encountered that meets the [end condition]. If the first line -meets both the [start condition] and the [end condition], the block -will contain just that line. +There are seven kinds of [HTML block], which can be defined by their +start and end conditions. The block begins with a line that meets a +[start condition](@) (after up to three spaces optional indentation). +It ends with the first subsequent line that meets a matching [end +condition](@), or the last line of the document, or the last line of +the [container block](#container-blocks) containing the current HTML +block, if no line is encountered that meets the [end condition]. If +the first line meets both the [start condition] and the [end +condition], the block will contain just that line. 1. **Start condition:** line begins with the string `<script`, `<pre`, or `<style` (case-insensitive), followed by whitespace, @@ -2050,9 +2054,9 @@ the string `/>`.\ **End condition:** line is followed by a [blank line]. 7. **Start condition:** line begins with a complete [open tag] -or [closing tag] (with any [tag name] other than `script`, -`style`, or `pre`) followed only by [whitespace] -or the end of the line.\ +(with any [tag name] other than `script`, +`style`, or `pre`) or a complete [closing tag], +followed only by [whitespace] or the end of the line.\ **End condition:** line is followed by a [blank line]. HTML blocks continue until they are closed by their appropriate @@ -6107,7 +6111,8 @@ The following rules define emphasis and strong emphasis: [delimiter runs]. If one of the delimiters can both open and close emphasis, then the sum of the lengths of the delimiter runs containing the opening and closing delimiters - must not be a multiple of 3. + must not be a multiple of 3 unless both lengths are + multiples of 3. 10. Strong emphasis begins with a delimiter that [can open strong emphasis] and ends with a delimiter that @@ -6117,7 +6122,8 @@ The following rules define emphasis and strong emphasis: [delimiter runs]. If one of the delimiters can both open and close strong emphasis, then the sum of the lengths of the delimiter runs containing the opening and closing - delimiters must not be a multiple of 3. + delimiters must not be a multiple of 3 unless both lengths + are multiples of 3. 11. A literal `*` character cannot occur at the beginning or end of `*`-delimited emphasis or `**`-delimited strong emphasis, unless it @@ -6736,7 +6742,8 @@ is precluded by the condition that a delimiter that can both open and close (like the `*` after `foo`) cannot form emphasis if the sum of the lengths of the delimiter runs containing the opening and -closing delimiters is a multiple of 3. +closing delimiters is a multiple of 3 unless +both lengths are multiples of 3. For the same reason, we don't get two consecutive @@ -6776,6 +6783,23 @@ omitted: ```````````````````````````````` +When the lengths of the interior closing and opening +delimiter runs are *both* multiples of 3, though, +they can match to create emphasis: + +```````````````````````````````` example +foo***bar***baz +. +<p>foo<em><strong>bar</strong></em>baz</p> +```````````````````````````````` + +```````````````````````````````` example +foo******bar*********baz +. +<p>foo<strong><strong><strong>bar</strong></strong></strong>***baz</p> +```````````````````````````````` + + Indefinite levels of nesting are possible: ```````````````````````````````` example @@ -7314,12 +7338,13 @@ A [link destination](@) consists of either closing `>` that contains no line breaks or unescaped `<` or `>` characters, or -- a nonempty sequence of characters that does not include - ASCII space or control characters, and includes parentheses - only if (a) they are backslash-escaped or (b) they are part of - a balanced pair of unescaped parentheses. (Implementations - may impose limits on parentheses nesting to avoid performance - issues, but at least three levels of nesting should be supported.) +- a nonempty sequence of characters that does not start with + `<`, does not include ASCII space or control characters, and + includes parentheses only if (a) they are backslash-escaped or + (b) they are part of a balanced pair of unescaped parentheses. + (Implementations may impose limits on parentheses nesting to + avoid performance issues, but at least three levels of nesting + should be supported.) A [link title](@) consists of either @@ -7417,6 +7442,15 @@ bar>) bar>)</p> ```````````````````````````````` +Pointy brackets that enclose links must be unescaped: + +```````````````````````````````` example +[link](<foo\>) +. +<p>[link](<foo>)</p> +```````````````````````````````` + + Parentheses inside the link destination may be escaped: ```````````````````````````````` example @@ -9515,7 +9549,7 @@ closers: of the delimiter stack. If the closing node is removed, reset `current_position` to the next element in the stack. -- If none in found: +- If none is found: + Set `openers_bottom` to the element before `current_position`. (We know that there are no openers for this kind of closer up to and |