Skip to content

Handle deeply nested lists #95

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kivikakk merged 4 commits into from
Jun 20, 2018
Merged

Handle deeply nested lists #95

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d51bb0e
Optimize S_find_first_nonspace.
jgm Apr 15, 2018
02c7e76
pathological_tests.py: added test for deeply nested lists.
jgm Apr 15, 2018
9f8ef82
pathological_tests.py: make tests run faster.
jgm Apr 15, 2018
284a079
Merge remote-tracking branch 'upstream/master'
philipturnbull Apr 16, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 19 additions & 14 deletions src/blocks.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -755,22 +755,24 @@ static void S_find_first_nonspace(cmark_parser *parser, cmark_chunk *input) {
char c;
int chars_to_tab = TAB_STOP - (parser->column % TAB_STOP);

parser->first_nonspace = parser->offset;
parser->first_nonspace_column = parser->column;
while ((c = peek_at(input, parser->first_nonspace))) {
if (c == ' ') {
parser->first_nonspace += 1;
parser->first_nonspace_column += 1;
chars_to_tab = chars_to_tab - 1;
if (chars_to_tab == 0) {
if (parser->first_nonspace <= parser->offset) {
parser->first_nonspace = parser->offset;
parser->first_nonspace_column = parser->column;
while ((c = peek_at(input, parser->first_nonspace))) {
if (c == ' ') {
parser->first_nonspace += 1;
parser->first_nonspace_column += 1;
chars_to_tab = chars_to_tab - 1;
if (chars_to_tab == 0) {
chars_to_tab = TAB_STOP;
}
} else if (c == '\t') {
parser->first_nonspace += 1;
parser->first_nonspace_column += chars_to_tab;
chars_to_tab = TAB_STOP;
} else {
break;
}
} else if (c == '\t') {
parser->first_nonspace += 1;
parser->first_nonspace_column += chars_to_tab;
chars_to_tab = TAB_STOP;
} else {
break;
}
}

Expand Down Expand Up @@ -1373,6 +1375,9 @@ static void S_process_line(cmark_parser *parser, const unsigned char *buffer,

parser->offset = 0;
parser->column = 0;
parser->first_nonspace = 0;
parser->first_nonspace_column = 0;
parser->indent = 0;
parser->blank = false;
parser->partially_consumed_tab = false;

Expand Down
19 changes: 11 additions & 8 deletions test/pathological_tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,21 +69,24 @@ def badhash(ref):
"nested block quotes":
((("> " * 50000) + "a"),
re.compile("(<blockquote>\n){50000}")),
"deeply nested lists":
("".join(map(lambda x: (" " * x + "* a\n"), range(0,1000))),
re.compile("<ul>\n(<li>a\n<ul>\n){999}<li>a</li>\n</ul>\n(</li>\n</ul>\n){999}")),
"U+0000 in input":
("abc\u0000de\u0000",
re.compile("abc\ufffd?de\ufffd?")),
"backticks":
("".join(map(lambda x: ("e" + "`" * x), range(1,10000))),
("".join(map(lambda x: ("e" + "`" * x), range(1,5000))),
re.compile("^<p>[e`]*</p>\n$")),
"unclosed links A":
("[a](<b" * 50000,
re.compile("(\[a\]\(&lt;b){50000}")),
("[a](<b" * 30000,
re.compile("(\[a\]\(&lt;b){30000}")),
"unclosed links B":
("[a](b" * 50000,
re.compile("(\[a\]\(b){50000}")),
"many references":
("".join(map(lambda x: ("[" + str(x) + "]: u\n"), range(1,50000 * 16))) + "[0] " * 50000,
re.compile("(\[0\] ){49999}")),
("[a](b" * 30000,
re.compile("(\[a\]\(b){30000}")),
# "many references":
# ("".join(map(lambda x: ("[" + str(x) + "]: u\n"), range(1,5000 * 16))) + "[0] " * 5000,
# re.compile("(\[0\] ){4999}")),
"reference collisions": hash_collisions()
}

Expand Down