commonmarker 0.17.7 → 0.17.7.1

data/ext/commonmarker/cmark-upstream/test/fuzzing_dictionary

@@ -1,49 +0,0 @@
-asterisk="*"
-attr_generic=" a=\"1\""
-attr_href=" href=\"1\""
-attr_xml_lang=" xml:lang=\"1\""
-attr_xmlns=" xmlns=\"1\""
-backslash="\\"
-backtick="`"
-colon=":"
-dashes="---"
-double_quote="\""
-entity_builtin="<"
-entity_decimal=""
-entity_external="&a;"
-entity_hex=""
-equals="==="
-exclamation="!"
-greater_than=">"
-hash="#"
-hyphen="-"
-indent="  "
-left_bracket="["
-left_paren="("
-less_than="<"
-plus="+"
-right_bracket="]"
-right_paren=")"
-single_quote="'"
-string_any="ANY"
-string_brackets="[]"
-string_cdata="CDATA"
-string_dashes="--"
-string_empty_dblquotes="\"\""
-string_empty_quotes="''"
-string_idrefs="IDREFS"
-string_parentheses="()"
-string_pcdata="#PCDATA"
-tag_cdata="<![CDATA["
-tag_close="</a>"
-tag_doctype="<!DOCTYPE"
-tag_element="<!ELEMENT"
-tag_entity="<!ENTITY"
-tag_notation="<!NOTATION"
-tag_open="<a>"
-tag_open_close="<a />"
-tag_open_exclamation="<!"
-tag_open_q="<?"
-tag_sq2_close="]]>"
-tag_xml_q="<?xml?>"
-underscore="_"

data/ext/commonmarker/cmark-upstream/test/normalize.py

@@ -1,194 +0,0 @@
-# -*- coding: utf-8 -*-
-from html.parser import HTMLParser
-import urllib
-
-try:
-    from html.parser import HTMLParseError
-except ImportError:
-    # HTMLParseError was removed in Python 3.5. It could never be
-    # thrown, so we define a placeholder instead.
-    class HTMLParseError(Exception):
-        pass
-
-from html.entities import name2codepoint
-import sys
-import re
-import cgi
-
-# Normalization code, adapted from
-# https://github.com/karlcow/markdown-testsuite/
-significant_attrs = ["alt", "href", "src", "title"]
-whitespace_re = re.compile('\s+')
-class MyHTMLParser(HTMLParser):
-    def __init__(self):
-        HTMLParser.__init__(self)
-        self.convert_charrefs = False
-        self.last = "starttag"
-        self.in_pre = False
-        self.output = ""
-        self.last_tag = ""
-    def handle_data(self, data):
-        after_tag = self.last == "endtag" or self.last == "starttag"
-        after_block_tag = after_tag and self.is_block_tag(self.last_tag)
-        if after_tag and self.last_tag == "br":
-            data = data.lstrip('\n')
-        if not self.in_pre:
-            data = whitespace_re.sub(' ', data)
-        if after_block_tag and not self.in_pre:
-            if self.last == "starttag":
-                data = data.lstrip()
-            elif self.last == "endtag":
-                data = data.strip()
-        self.output += data
-        self.last = "data"
-    def handle_endtag(self, tag):
-        if tag == "pre":
-            self.in_pre = False
-        elif self.is_block_tag(tag):
-            self.output = self.output.rstrip()
-        self.output += "</" + tag + ">"
-        self.last_tag = tag
-        self.last = "endtag"
-    def handle_starttag(self, tag, attrs):
-        if tag == "pre":
-            self.in_pre = True
-        if self.is_block_tag(tag):
-            self.output = self.output.rstrip()
-        self.output += "<" + tag
-        # For now we don't strip out 'extra' attributes, because of
-        # raw HTML test cases.
-        # attrs = filter(lambda attr: attr[0] in significant_attrs, attrs)
-        if attrs:
-            attrs.sort()
-            for (k,v) in attrs:
-                self.output += " " + k
-                if v in ['href','src']:
-                    self.output += ("=" + '"' +
-                            urllib.quote(urllib.unquote(v), safe='/') + '"')
-                elif v != None:
-                    self.output += ("=" + '"' + cgi.escape(v,quote=True) + '"')
-        self.output += ">"
-        self.last_tag = tag
-        self.last = "starttag"
-    def handle_startendtag(self, tag, attrs):
-        """Ignore closing tag for self-closing """
-        self.handle_starttag(tag, attrs)
-        self.last_tag = tag
-        self.last = "endtag"
-    def handle_comment(self, data):
-        self.output += '<!--' + data + '-->'
-        self.last = "comment"
-    def handle_decl(self, data):
-        self.output += '<!' + data + '>'
-        self.last = "decl"
-    def unknown_decl(self, data):
-        self.output += '<!' + data + '>'
-        self.last = "decl"
-    def handle_pi(self,data):
-        self.output += '<?' + data + '>'
-        self.last = "pi"
-    def handle_entityref(self, name):
-        try:
-            c = chr(name2codepoint[name])
-        except KeyError:
-            c = None
-        self.output_char(c, '&' + name + ';')
-        self.last = "ref"
-    def handle_charref(self, name):
-        try:
-            if name.startswith("x"):
-                c = chr(int(name[1:], 16))
-            else:
-                c = chr(int(name))
-        except ValueError:
-                c = None
-        self.output_char(c, '&' + name + ';')
-        self.last = "ref"
-    # Helpers.
-    def output_char(self, c, fallback):
-        if c == '<':
-            self.output += "&lt;"
-        elif c == '>':
-            self.output += "&gt;"
-        elif c == '&':
-            self.output += "&amp;"
-        elif c == '"':
-            self.output += "&quot;"
-        elif c == None:
-            self.output += fallback
-        else:
-            self.output += c
-
-    def is_block_tag(self,tag):
-        return (tag in ['article', 'header', 'aside', 'hgroup', 'blockquote',
-            'hr', 'iframe', 'body', 'li', 'map', 'button', 'object', 'canvas',
-            'ol', 'caption', 'output', 'col', 'p', 'colgroup', 'pre', 'dd',
-            'progress', 'div', 'section', 'dl', 'table', 'td', 'dt',
-            'tbody', 'embed', 'textarea', 'fieldset', 'tfoot', 'figcaption',
-            'th', 'figure', 'thead', 'footer', 'tr', 'form', 'ul',
-            'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'video', 'script', 'style'])
-
-def normalize_html(html):
-    r"""
-    Return normalized form of HTML which ignores insignificant output
-    differences:
-
-    Multiple inner whitespaces are collapsed to a single space (except
-    in pre tags):
-
-        >>> normalize_html("<p>a  \t b</p>")
-        '<p>a b</p>'
-
-        >>> normalize_html("<p>a  \t\nb</p>")
-        '<p>a b</p>'
-
-    * Whitespace surrounding block-level tags is removed.
-
-        >>> normalize_html("<p>a  b</p>")
-        '<p>a b</p>'
-
-        >>> normalize_html(" <p>a  b</p>")
-        '<p>a b</p>'
-
-        >>> normalize_html("<p>a  b</p> ")
-        '<p>a b</p>'
-
-        >>> normalize_html("\n\t<p>\n\t\ta  b\t\t</p>\n\t")
-        '<p>a b</p>'
-
-        >>> normalize_html("<i>a  b</i> ")
-        '<i>a b</i> '
-
-    * Self-closing tags are converted to open tags.
-
-        >>> normalize_html("<br />")
-        '<br>'
-
-    * Attributes are sorted and lowercased.
-
-        >>> normalize_html('<a title="bar" HREF="foo">x</a>')
-        '<a href="foo" title="bar">x</a>'
-
-    * References are converted to unicode, except that '<', '>', '&', and
-      '"' are rendered using entities.
-
-        >>> normalize_html("&forall;&amp;&gt;&lt;&quot;")
-        '\u2200&amp;&gt;&lt;&quot;'
-
-    """
-    html_chunk_re = re.compile("(\<!\[CDATA\[.*?\]\]\>|\<[^>]*\>|[^<]+)")
-    try:
-        parser = MyHTMLParser()
-        # We work around HTMLParser's limitations parsing CDATA
-        # by breaking the input into chunks and passing CDATA chunks
-        # through verbatim.
-        for chunk in re.finditer(html_chunk_re, html):
-            if chunk.group(0)[:8] == "<![CDATA":
-                parser.output += chunk.group(0)
-            else:
-                parser.feed(chunk.group(0))
-        parser.close()
-        return parser.output
-    except HTMLParseError as e:
-        sys.stderr.write("Normalization error: " + e.msg + "\n")
-        return html  # on error, return unnormalized HTML

data/ext/commonmarker/cmark-upstream/test/pathological_tests.py

@@ -1,145 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-
-import re
-import argparse
-import sys
-import platform
-import itertools
-import multiprocessing
-from cmark import CMark
-
-def hash_collisions():
-    REFMAP_SIZE = 16
-    COUNT = 50000
-
-    def badhash(ref):
-        h = 0
-        for c in ref:
-            a = (h << 6) & 0xFFFFFFFF
-            b = (h << 16) & 0xFFFFFFFF
-            h = ord(c) + a + b - h
-            h = h & 0xFFFFFFFF
-
-        return (h % REFMAP_SIZE) == 0
-
-    keys = ("x%d" % i for i in itertools.count())
-    collisions = itertools.islice((k for k in keys if badhash(k)), COUNT)
-    bad_key = next(collisions)
-
-    document = ''.join("[%s]: /url\n\n[%s]\n\n" % (key, bad_key) for key in collisions)
-
-    return document, re.compile("(<p>\[%s\]</p>\n){%d}" % (bad_key, COUNT-1))
-
-allowed_failures = {"many references": True}
-
-# list of pairs consisting of input and a regex that must match the output.
-pathological = {
-    # note - some pythons have limit of 65535 for {num-matches} in re.
-    "nested strong emph":
-                (("*a **a " * 65000) + "b" + (" a** a*" * 65000),
-                 re.compile("(<em>a <strong>a ){65000}b( a</strong> a</em>){65000}")),
-    "many emph closers with no openers":
-                 (("a_ " * 65000),
-                  re.compile("(a[_] ){64999}a_")),
-    "many emph openers with no closers":
-                 (("_a " * 65000),
-                  re.compile("(_a ){64999}_a")),
-    "many link closers with no openers":
-                 (("a]" * 65000),
-                  re.compile("(a\]){65000}")),
-    "many link openers with no closers":
-                 (("[a" * 65000),
-                  re.compile("(\[a){65000}")),
-    "mismatched openers and closers":
-                 (("*a_ " * 50000),
-                  re.compile("([*]a[_] ){49999}[*]a_")),
-    "openers and closers multiple of 3":
-                 (("a**b" + ("c* " * 50000)),
-                  re.compile("a[*][*]b(c[*] ){49999}c[*]")),
-    "link openers and emph closers":
-                 (("[ a_" * 50000),
-                  re.compile("(\[ a_){50000}")),
-    "hard link/emph case":
-                 ("**x [a*b**c*](d)",
-                  re.compile("\\*\\*x <a href=\"d\">a<em>b\\*\\*c</em></a>")),
-    "nested brackets":
-                 (("[" * 50000) + "a" + ("]" * 50000),
-                  re.compile("\[{50000}a\]{50000}")),
-    "nested block quotes":
-                 ((("> " * 50000) + "a"),
-                  re.compile("(<blockquote>\n){50000}")),
-    "U+0000 in input":
-                 ("abc\u0000de\u0000",
-                  re.compile("abc\ufffd?de\ufffd?")),
-    "backticks":
-                 ("".join(map(lambda x: ("e" + "`" * x), range(1,10000))),
-                  re.compile("^<p>[e`]*</p>\n$")),
-    "unclosed links A":
-                 ("[a](<b" * 50000,
-                  re.compile("(\[a\]\(&lt;b){50000}")),
-    "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}")),
-    "reference collisions": hash_collisions()
-    }
-
-whitespace_re = re.compile('/s+/')
-passed = 0
-errored = 0
-ignored = 0
-TIMEOUT = 5
-
-def run_test(inp, regex):
-    parser = argparse.ArgumentParser(description='Run cmark tests.')
-    parser.add_argument('--program', dest='program', nargs='?', default=None,
-            help='program to test')
-    parser.add_argument('--library-dir', dest='library_dir', nargs='?',
-            default=None, help='directory containing dynamic library')
-    args = parser.parse_args(sys.argv[1:])
-    cmark = CMark(prog=args.program, library_dir=args.library_dir)
-
-    [rc, actual, err] = cmark.to_html(inp)
-    if rc != 0:
-        print('[ERRORED (return code %d)]' % rc)
-        print(err)
-        exit(1)
-    elif regex.search(actual):
-        print('[PASSED]')
-    else:
-        print('[FAILED (mismatch)]')
-        print(repr(actual))
-        exit(1)
-
-if __name__ == '__main__':
-    print("Testing pathological cases:")
-    for description in pathological:
-        (inp, regex) = pathological[description]
-        print(description, "... ", end='')
-        sys.stdout.flush()
-
-        p = multiprocessing.Process(target=run_test, args=(inp, regex))
-        p.start()
-        p.join(TIMEOUT)
-
-        if p.is_alive():
-            p.terminate()
-            p.join()
-            print('[TIMED OUT]')
-            if allowed_failures[description]:
-                ignored += 1
-            else:
-                errored += 1
-        elif p.exitcode != 0:
-            if allowed_failures[description]:
-                ignored += 1
-            else:
-                errored += 1
-        else:
-            passed += 1
-
-    print("%d passed, %d errored, %d ignored" % (passed, errored, ignored))
-    exit(errored)

data/ext/commonmarker/cmark-upstream/test/regression.txt

@@ -1,128 +0,0 @@
-### Regression tests
-
-Issue #113: EOL character weirdness on Windows
-(Important: first line ends with CR + CR + LF)
-
-```````````````````````````````` example
-line1
-line2
-.
-<p>line1</p>
-<p>line2</p>
-````````````````````````````````
-
-Issue #114: cmark skipping first character in line
-(Important: the blank lines around "Repeatedly" contain a tab.)
-
-```````````````````````````````` example
-By taking it apart
-
-- alternative solutions
-→
-Repeatedly solving
-→
-- how techniques
-.
-<p>By taking it apart</p>
-<ul>
-<li>alternative solutions</li>
-</ul>
-<p>Repeatedly solving</p>
-<ul>
-<li>how techniques</li>
-</ul>
-````````````````````````````````
-
-Issue jgm/CommonMark#430:  h2..h6 not recognized as block tags.
-
-```````````````````````````````` example
-<h1>lorem</h1>
-
-<h2>lorem</h2>
-
-<h3>lorem</h3>
-
-<h4>lorem</h4>
-
-<h5>lorem</h5>
-
-<h6>lorem</h6>
-.
-<h1>lorem</h1>
-<h2>lorem</h2>
-<h3>lorem</h3>
-<h4>lorem</h4>
-<h5>lorem</h5>
-<h6>lorem</h6>
-````````````````````````````````
-
-Issue jgm/commonmark.js#109 - tabs after setext header line
-
-
-```````````````````````````````` example
-hi
---→
-.
-<h2>hi</h2>
-````````````````````````````````
-
-Issue #177 - incorrect emphasis parsing
-
-```````````````````````````````` example
-a***b* c*
-.
-<p>a*<em><em>b</em> c</em></p>
-````````````````````````````````
-
-Issue #193 - unescaped left angle brackets in link destination
-
-```````````````````````````````` example
-[a]
-
-[a]: <te<st>
-.
-<p><a href="%3Cte%3Cst%3E">a</a></p>
-````````````````````````````````
-
-Issue #192 - escaped spaces in link destination
-
-
-```````````````````````````````` example
-[a](te\ st)
-.
-<p>[a](te\ st)</p>
-````````````````````````````````
-
-Issue github/github#76615:  multiple delimiter combinations gets sketchy
-
-
-```````````````````````````````` example strikethrough
-~~**_`this`_**~~  
-~~***`this`***~~  
-~~___`this`___~~
-
-**_`this`_**  
-***`this`***  
-___`this`___
-
-~~**_this_**~~  
-~~***this***~~  
-~~___this___~~
-
-**_this_**  
-***this***  
-___this___
-.
-<p><del><strong><em><code>this</code></em></strong></del><br />
-<del><em><strong><code>this</code></strong></em></del><br />
-<del><em><strong><code>this</code></strong></em></del></p>
-<p><strong><em><code>this</code></em></strong><br />
-<em><strong><code>this</code></strong></em><br />
-<em><strong><code>this</code></strong></em></p>
-<p><del><strong><em>this</em></strong></del><br />
-<del><em><strong>this</strong></em></del><br />
-<del><em><strong>this</strong></em></del></p>
-<p><strong><em>this</em></strong><br />
-<em><strong>this</strong></em><br />
-<em><strong>this</strong></em></p>
-````````````````````````````````