commonmarker 0.0.1

data/ext/commonmarker/cmark/test/afl_dictionary/backtick

@@ -0,0 +1 @@
+`

data/ext/commonmarker/cmark/test/afl_dictionary/colon

@@ -0,0 +1 @@
+:

data/ext/commonmarker/cmark/test/afl_dictionary/dashes

@@ -0,0 +1 @@
+---

data/ext/commonmarker/cmark/test/afl_dictionary/double_quote

@@ -0,0 +1 @@
+"

data/ext/commonmarker/cmark/test/afl_dictionary/entity_builtin

@@ -0,0 +1 @@
+<

data/ext/commonmarker/cmark/test/afl_dictionary/entity_decimal

@@ -0,0 +1 @@
+

data/ext/commonmarker/cmark/test/afl_dictionary/entity_external

@@ -0,0 +1 @@
+&a;

data/ext/commonmarker/cmark/test/afl_dictionary/entity_hex

@@ -0,0 +1 @@
+

data/ext/commonmarker/cmark/test/afl_dictionary/equals

@@ -0,0 +1 @@
+===

data/ext/commonmarker/cmark/test/afl_dictionary/exclamation

@@ -0,0 +1 @@
+!

data/ext/commonmarker/cmark/test/afl_dictionary/greater_than

@@ -0,0 +1 @@
+>

data/ext/commonmarker/cmark/test/afl_dictionary/hash

@@ -0,0 +1 @@
+#

data/ext/commonmarker/cmark/test/afl_dictionary/indent

@@ -0,0 +1 @@
+  

data/ext/commonmarker/cmark/test/afl_dictionary/left_bracket

@@ -0,0 +1 @@
+[

data/ext/commonmarker/cmark/test/afl_dictionary/left_paren

@@ -0,0 +1 @@
+(

data/ext/commonmarker/cmark/test/afl_dictionary/less_than

@@ -0,0 +1 @@
+<

data/ext/commonmarker/cmark/test/afl_dictionary/plus

@@ -0,0 +1 @@
++

data/ext/commonmarker/cmark/test/afl_dictionary/right_bracket

@@ -0,0 +1 @@
+]

data/ext/commonmarker/cmark/test/afl_dictionary/right_paren

@@ -0,0 +1 @@
+)

data/ext/commonmarker/cmark/test/afl_dictionary/single_quote

@@ -0,0 +1 @@
+'

data/ext/commonmarker/cmark/test/afl_dictionary/string_any

@@ -0,0 +1 @@
+ANY

data/ext/commonmarker/cmark/test/afl_dictionary/string_brackets

@@ -0,0 +1 @@
+[]

data/ext/commonmarker/cmark/test/afl_dictionary/string_cdata

@@ -0,0 +1 @@
+CDATA

data/ext/commonmarker/cmark/test/afl_dictionary/string_dashes

@@ -0,0 +1 @@
+--

data/ext/commonmarker/cmark/test/afl_dictionary/string_empty_dblquotes

@@ -0,0 +1 @@
+""

data/ext/commonmarker/cmark/test/afl_dictionary/string_empty_quotes

@@ -0,0 +1 @@
+''

data/ext/commonmarker/cmark/test/afl_dictionary/string_idrefs

@@ -0,0 +1 @@
+IDREFS

data/ext/commonmarker/cmark/test/afl_dictionary/string_parentheses

@@ -0,0 +1 @@
+()

data/ext/commonmarker/cmark/test/afl_dictionary/string_pcdata

@@ -0,0 +1 @@
+#PCDATA

data/ext/commonmarker/cmark/test/afl_dictionary/tag_cdata

@@ -0,0 +1 @@
+<![CDATA[

data/ext/commonmarker/cmark/test/afl_dictionary/tag_close

@@ -0,0 +1 @@
+</a>

data/ext/commonmarker/cmark/test/afl_dictionary/tag_doctype

@@ -0,0 +1 @@
+<!DOCTYPE

data/ext/commonmarker/cmark/test/afl_dictionary/tag_element

@@ -0,0 +1 @@
+<!ELEMENT

data/ext/commonmarker/cmark/test/afl_dictionary/tag_entity

@@ -0,0 +1 @@
+<!ENTITY

data/ext/commonmarker/cmark/test/afl_dictionary/tag_notation

@@ -0,0 +1 @@
+<!NOTATION

data/ext/commonmarker/cmark/test/afl_dictionary/tag_open

@@ -0,0 +1 @@
+<a>

data/ext/commonmarker/cmark/test/afl_dictionary/tag_open_close

@@ -0,0 +1 @@
+<a />

data/ext/commonmarker/cmark/test/afl_dictionary/tag_open_exclamation

@@ -0,0 +1 @@
+<!

data/ext/commonmarker/cmark/test/afl_dictionary/tag_open_q

@@ -0,0 +1 @@
+<?

data/ext/commonmarker/cmark/test/afl_dictionary/tag_sq2_close

@@ -0,0 +1 @@
+]]>

data/ext/commonmarker/cmark/test/afl_dictionary/tag_xml_q

@@ -0,0 +1 @@
+<?xml?>

data/ext/commonmarker/cmark/test/afl_dictionary/underscore

@@ -0,0 +1 @@
+_

data/ext/commonmarker/cmark/test/afl_test_cases/test.md

@@ -0,0 +1,36 @@
+# H1
+
+H2
+--
+
+t ☺  
+*b* **em** `c`
+≥\&\
+\_e\_
+
+4) I1
+
+5) I2
+   > [l](/u "t")
+   >
+   > - [f]
+   > - ![a](/u "t")
+   >
+   >> <ftp://hh>
+   >> <u@hh>
+
+~~~ l☺
+cb
+~~~
+
+    c1
+    c2
+
+***
+
+<div>
+<b>x</b>
+</div>
+
+[f]: /u "t"
+

data/ext/commonmarker/cmark/test/cmark.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+from ctypes import CDLL, c_char_p, c_long
+from subprocess import *
+import platform
+import os
+
+def pipe_through_prog(prog, text):
+    p1 = Popen(prog.split(), stdout=PIPE, stdin=PIPE, stderr=PIPE)
+    [result, err] = p1.communicate(input=text.encode('utf-8'))
+    return [p1.returncode, result.decode('utf-8'), err]
+
+def use_library(lib, text):
+    textbytes = text.encode('utf-8')
+    textlen = len(textbytes)
+    return [0, lib(textbytes, textlen, 0).decode('utf-8'), '']
+
+class CMark:
+    def __init__(self, prog=None, library_dir=None):
+        self.prog = prog
+        if prog:
+            self.to_html = lambda x: pipe_through_prog(prog, x)
+        else:
+            sysname = platform.system()
+            if sysname == 'Darwin':
+                libname = "libcmark.dylib"
+            elif sysname == 'Windows':
+                libname = "cmark.dll"
+            else:
+                libname = "libcmark.so"
+            if library_dir:
+                libpath = os.path.join(library_dir, libname)
+            else:
+                libpath = os.path.join("build", "src", libname)
+            cmark = CDLL(libpath)
+            markdown = cmark.cmark_markdown_to_html
+            markdown.restype = c_char_p
+            markdown.argtypes = [c_char_p, c_long]
+            self.to_html = lambda x: use_library(markdown, x)

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

@@ -0,0 +1,179 @@
+# -*- coding: utf-8 -*-
+from html.parser import HTMLParser, HTMLParseError
+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.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')
+        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 != 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/test/pathological_tests.py

@@ -0,0 +1,63 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+import re
+import argparse
+import sys
+import platform
+from cmark import CMark
+
+if __name__ == "__main__":
+    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)
+
+# 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}")),
+    "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?"))
+    }
+
+whitespace_re = re.compile('/s+/')
+passed = 0
+errored = 0
+failed = 0
+
+print("Testing pathological cases:")
+for description in pathological:
+    print(description)
+    (inp, regex) = pathological[description]
+    [rc, actual, err] = cmark.to_html(inp)
+    if rc != 0:
+        errored += 1
+        print(description)
+        print("program returned error code %d" % rc)
+        print(err)
+    elif regex.search(actual):
+        passed += 1
+    else:
+        print(description, 'failed')
+        print(repr(actual))
+        failed += 1
+
+print("%d passed, %d failed, %d errored" % (passed, failed, errored))
+if (failed == 0 and errored == 0):
+    exit(0)
+else:
+    exit(1)

data/ext/commonmarker/cmark/test/roundtrip.sh

@@ -0,0 +1,2 @@
+#!/bin/sh
+./build/src/cmark -t commonmark | ./build/src/cmark

data/ext/commonmarker/cmark/test/smart_punct.txt

@@ -0,0 +1,96 @@
+## Smart punctuation
+
+.
+"Hello," said the spider.
+"'Shelob' is my name."
+.
+<p>“Hello,” said the spider.
+“‘Shelob’ is my name.”</p>
+.
+
+.
+'A', 'B', and 'C' are letters.
+.
+<p>‘A’, ‘B’, and ‘C’ are letters.</p>
+.
+
+.
+'Oak,' 'elm,' and 'beech' are names of trees.
+So is 'pine.'
+.
+<p>‘Oak,’ ‘elm,’ and ‘beech’ are names of trees.
+So is ‘pine.’</p>
+.
+
+.
+'He said, "I want to go."'
+.
+<p>‘He said, “I want to go.”’</p>
+.
+
+.
+Were you alive in the 70's?
+.
+<p>Were you alive in the 70’s?</p>
+.
+
+.
+Here is some quoted '`code`' and a "[quoted link](url)".
+.
+<p>Here is some quoted ‘<code>code</code>’ and a “<a href="url">quoted link</a>”.</p>
+.
+
+.
+'tis the season to be 'jolly'
+.
+<p>’tis the season to be ‘jolly’</p>
+.
+
+.
+"A paragraph with no closing quote.
+
+"Second paragraph by same speaker, in fiction."
+.
+<p>“A paragraph with no closing quote.</p>
+<p>“Second paragraph by same speaker, in fiction.”</p>
+.
+
+.
+\"This is not smart.\"
+This isn\'t either.
+.
+<p>&quot;This is not smart.&quot;
+This isn't either.</p>
+.
+
+.
+Some dashes:  one---two ---
+three---four --- five.
+.
+<p>Some dashes:  one—two —
+three—four — five.</p>
+.
+
+.
+Escaped dashes: \-- \-\-\-.
+.
+<p>Escaped dashes: -- ---.</p>
+.
+
+.
+Dashes between numbers: 5--7, 255--66, 1987--1999.
+.
+<p>Dashes between numbers: 5–7, 255–66, 1987–1999.</p>
+.
+
+.
+Ellipses...and...and....
+.
+<p>Ellipses…and…and….</p>
+.
+
+.
+No ellipses\.\.\.
+.
+<p>No ellipses...</p>
+.