From c301f6b6c6c3c870bc7a56334c3fd1d42356b736 Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Sat, 29 Nov 2014 11:00:48 -0800 Subject: Moved testing programs to test/. Added test/CMakeLists.txt. --- CMakeLists.txt | 22 +--- pathological_tests.py | 82 ------------ spec_tests.py | 308 --------------------------------------------- test/CMakeLists.txt | 24 ++++ test/pathological_tests.py | 82 ++++++++++++ test/spec_tests.py | 308 +++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 415 insertions(+), 411 deletions(-) delete mode 100644 pathological_tests.py delete mode 100755 spec_tests.py create mode 100644 test/CMakeLists.txt create mode 100644 test/pathological_tests.py create mode 100755 test/spec_tests.py diff --git a/CMakeLists.txt b/CMakeLists.txt index 2e4c870..be75c5e 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -15,28 +15,8 @@ set(PROJECT_VERSION ${PROJECT_VERSION_MAJOR}.${PROJECT_VERSION_MINOR}.${PROJECT_ add_subdirectory(src) add_subdirectory(api_test) add_subdirectory(man) - enable_testing() - -# To get verbose output: cmake --build build --target "test" -- ARGS='-V' -add_test(spectest_library - python "${CMAKE_SOURCE_DIR}/spec_tests.py" "--no-normalize" "--spec" - "${CMAKE_SOURCE_DIR}/spec.txt" "--library-dir" "${CMAKE_BINARY_DIR}/src" -) -add_test(pathological_tests_library - python "${CMAKE_SOURCE_DIR}/pathological_tests.py" - "--library-dir" "${CMAKE_BINARY_DIR}/src" -) -add_test(NAME api_test COMMAND api_test) -if (WIN32) - file(TO_NATIVE_PATH ${CMAKE_BINARY_DIR}/src WIN_DLL_DIR) - set_tests_properties(api_test PROPERTIES - ENVIRONMENT "PATH=${WIN_DLL_DIR};$ENV{PATH}" - ) -endif(WIN32) -add_test(spectest_executable - python "${CMAKE_SOURCE_DIR}/spec_tests.py" "--no-normalize" "--spec" "${CMAKE_SOURCE_DIR}/spec.txt" "--program" "${CMAKE_BINARY_DIR}/src/cmark" -) +add_subdirectory(test) if(NOT CMAKE_BUILD_TYPE) set(CMAKE_BUILD_TYPE "Release" CACHE STRING diff --git a/pathological_tests.py b/pathological_tests.py deleted file mode 100644 index 999a467..0000000 --- a/pathological_tests.py +++ /dev/null @@ -1,82 +0,0 @@ -#!/usr/bin/env python -# -*- coding: utf-8 -*- - -from ctypes import CDLL, c_char_p, c_long -from subprocess import * -import re -import argparse -import sys -import platform - -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:]) - -if not args.program: - sysname = platform.system() - libname = "libcmark" - if sysname == 'Darwin': - libname += ".dylib" - elif sysname == 'Windows': - libname += ".dll" - else: - libname += ".so" - if args and args.library_dir: - libpath = args.library_dir + "/" + libname - else: - libpath = "build/src/" + libname - cmark = CDLL(libpath) - - markdown = cmark.cmark_markdown_to_html - markdown.restype = c_char_p - markdown.argtypes = [c_char_p, c_long] - -def md2html(text, prog): - if prog: - p1 = Popen(prog.split(), stdout=PIPE, stdin=PIPE, stderr=PIPE) - [result, err] = p1.communicate(input=text) - return [p1.returncode, result, err] - else: - return [0, markdown(text, len(text)), ''] - -pathological = { - "nested strong emph": - (("*a **a " * 100000) + "b" + (" a** a*" * 100000), - "

" + ("a a " * 100000) + "b" + - (" a a" * 100000) + "

"), - "nested brackets": - (("[" * 50000) + "a" + ("]" * 50000), - "

" + ("[" * 50000) + "a" + ("]" * 50000) + "

") - } - -whitespace_re = re.compile('/s+/') -passed = 0 -errored = 0 -failed = 0 - -print "Testing pathological cases:" -for description in pathological: - print description - (inp, expected) = pathological[description] - [rc, actual, err] = md2html(inp, args.program) - if rc != 0: - errored += 1 - print description - print "program returned error code %d" % rc - print(err) - elif whitespace_re.sub(' ', actual.rstrip()) == expected.rstrip(): - passed += 1 - else: - print description, 'failed' - print(actual) - failed += 1 - -print "%d passed, %d failed, %d errored" % (passed, failed, errored) -if (failed == 0 and errored == 0): - exit(0) -else: - exit(1) diff --git a/spec_tests.py b/spec_tests.py deleted file mode 100755 index 6e0d4cc..0000000 --- a/spec_tests.py +++ /dev/null @@ -1,308 +0,0 @@ -#!/usr/bin/env python -# -*- coding: utf-8 -*- - -from ctypes import CDLL, c_char_p, c_long -import sys -import platform -from difflib import unified_diff -from subprocess import * -import argparse -from HTMLParser import HTMLParser, HTMLParseError -from htmlentitydefs import name2codepoint -import re -import cgi -import json - -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('--spec', dest='spec', nargs='?', default='spec.txt', - help='path to spec') - parser.add_argument('--pattern', dest='pattern', nargs='?', - default=None, help='limit to sections matching regex pattern') - parser.add_argument('--library-dir', dest='library_dir', nargs='?', - default=None, help='directory containing dynamic library') - parser.add_argument('--no-normalize', dest='normalize', - action='store_const', const=False, default=True, - help='do not normalize HTML') - parser.add_argument('--dump-tests', dest='dump_tests', - action='store_const', const=True, default=False, - help='dump tests in JSON format') - parser.add_argument('--debug-normalization', dest='debug_normalization', - action='store_const', const=True, - default=False, help='filter stdin through normalizer for testing') - args = parser.parse_args(sys.argv[1:]) - -if not (args.program or args.dump_tests or args.debug_normalization): - sysname = platform.system() - libname = "libcmark" - if sysname == 'Darwin': - libname += ".dylib" - elif sysname == 'Windows': - libname += ".dll" - else: - libname += ".so" - if args and args.library_dir: - libpath = args.library_dir + "/" + libname - else: - libpath = "build/src/" + libname - cmark = CDLL(libpath) - - markdown = cmark.cmark_markdown_to_html - markdown.restype = c_char_p - markdown.argtypes = [c_char_p, c_long] - -def md2html(text, prog): - if prog: - p1 = Popen(prog.split(), stdout=PIPE, stdin=PIPE, stderr=PIPE) - [result, err] = p1.communicate(input=text) - return [p1.returncode, result, err] - else: - return [0, markdown(text, len(text)), ''] - -# 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 = u"" - 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 - if self.is_block_tag(tag): - self.output = self.output.rstrip() - self.output += "" - self.last_tag = tag - self.last = "endtag" - def handle_starttag(self, tag, attrs): - if tag == "pre": - self.in_pre = True - 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 += '' - self.last = "comment" - def handle_decl(self, data): - self.output += '' - self.last = "decl" - def unknown_decl(self, data): - self.output += '' - self.last = "decl" - def handle_pi(self,data): - self.output += '' - self.last = "pi" - def handle_entityref(self, name): - try: - c = unichr(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 = unichr(int(name[1:], 16)) - else: - c = unichr(int(name)) - except ValueError: - c = None - self.output_char(c, '&' + name + ';') - self.last = "ref" - # Helpers. - def output_char(self, c, fallback): - if c == u'<': - self.output += "<" - elif c == u'>': - self.output += ">" - elif c == u'&': - self.output += "&" - elif c == u'"': - self.output += """ - 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). - * Outer whitespace (outside block-level tags) is removed. - * Self-closing tags are converted to open tags. - * Attributes are sorted and lowercased. - * References are converted to unicode, except that '<', '>', '&', and - '&' are rendered using entities. - """ - html_chunk_re = re.compile("(\|\<[^>]*\>|[^<]+)") - 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] == "" + ("a a " * 100000) + "b" + + (" a a" * 100000) + "

"), + "nested brackets": + (("[" * 50000) + "a" + ("]" * 50000), + "

" + ("[" * 50000) + "a" + ("]" * 50000) + "

") + } + +whitespace_re = re.compile('/s+/') +passed = 0 +errored = 0 +failed = 0 + +print "Testing pathological cases:" +for description in pathological: + print description + (inp, expected) = pathological[description] + [rc, actual, err] = md2html(inp, args.program) + if rc != 0: + errored += 1 + print description + print "program returned error code %d" % rc + print(err) + elif whitespace_re.sub(' ', actual.rstrip()) == expected.rstrip(): + passed += 1 + else: + print description, 'failed' + print(actual) + failed += 1 + +print "%d passed, %d failed, %d errored" % (passed, failed, errored) +if (failed == 0 and errored == 0): + exit(0) +else: + exit(1) diff --git a/test/spec_tests.py b/test/spec_tests.py new file mode 100755 index 0000000..6e0d4cc --- /dev/null +++ b/test/spec_tests.py @@ -0,0 +1,308 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- + +from ctypes import CDLL, c_char_p, c_long +import sys +import platform +from difflib import unified_diff +from subprocess import * +import argparse +from HTMLParser import HTMLParser, HTMLParseError +from htmlentitydefs import name2codepoint +import re +import cgi +import json + +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('--spec', dest='spec', nargs='?', default='spec.txt', + help='path to spec') + parser.add_argument('--pattern', dest='pattern', nargs='?', + default=None, help='limit to sections matching regex pattern') + parser.add_argument('--library-dir', dest='library_dir', nargs='?', + default=None, help='directory containing dynamic library') + parser.add_argument('--no-normalize', dest='normalize', + action='store_const', const=False, default=True, + help='do not normalize HTML') + parser.add_argument('--dump-tests', dest='dump_tests', + action='store_const', const=True, default=False, + help='dump tests in JSON format') + parser.add_argument('--debug-normalization', dest='debug_normalization', + action='store_const', const=True, + default=False, help='filter stdin through normalizer for testing') + args = parser.parse_args(sys.argv[1:]) + +if not (args.program or args.dump_tests or args.debug_normalization): + sysname = platform.system() + libname = "libcmark" + if sysname == 'Darwin': + libname += ".dylib" + elif sysname == 'Windows': + libname += ".dll" + else: + libname += ".so" + if args and args.library_dir: + libpath = args.library_dir + "/" + libname + else: + libpath = "build/src/" + libname + cmark = CDLL(libpath) + + markdown = cmark.cmark_markdown_to_html + markdown.restype = c_char_p + markdown.argtypes = [c_char_p, c_long] + +def md2html(text, prog): + if prog: + p1 = Popen(prog.split(), stdout=PIPE, stdin=PIPE, stderr=PIPE) + [result, err] = p1.communicate(input=text) + return [p1.returncode, result, err] + else: + return [0, markdown(text, len(text)), ''] + +# 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 = u"" + 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 + if self.is_block_tag(tag): + self.output = self.output.rstrip() + self.output += "" + self.last_tag = tag + self.last = "endtag" + def handle_starttag(self, tag, attrs): + if tag == "pre": + self.in_pre = True + 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 += '' + self.last = "comment" + def handle_decl(self, data): + self.output += '' + self.last = "decl" + def unknown_decl(self, data): + self.output += '' + self.last = "decl" + def handle_pi(self,data): + self.output += '' + self.last = "pi" + def handle_entityref(self, name): + try: + c = unichr(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 = unichr(int(name[1:], 16)) + else: + c = unichr(int(name)) + except ValueError: + c = None + self.output_char(c, '&' + name + ';') + self.last = "ref" + # Helpers. + def output_char(self, c, fallback): + if c == u'<': + self.output += "<" + elif c == u'>': + self.output += ">" + elif c == u'&': + self.output += "&" + elif c == u'"': + self.output += """ + 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). + * Outer whitespace (outside block-level tags) is removed. + * Self-closing tags are converted to open tags. + * Attributes are sorted and lowercased. + * References are converted to unicode, except that '<', '>', '&', and + '&' are rendered using entities. + """ + html_chunk_re = re.compile("(\|\<[^>]*\>|[^<]+)") + 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] == "