def ordered_list():
return pg.AllOf(
pg.Ignore(pg.Optional(pg.Many("\n"))),
pg.Indented(pg.AllOf(
numbered_bullet,
pg.Optional(pg.Many(numbered_bullet, ordered_list))),
optional=True))
def test_escaped():
html_text = pg.NamedPattern(
'html_text',
pg.Many(
pg.Words(
pg.Words.letters+"</>")))
escaped_text = pg.NamedPattern(
'escaped_text',
pg.Escaped(html_text))
data = """<p>Some Text</p>"""
expected = [
'escaped_text',
['html_text',
"<p>Some Text</p>"]]
result = pg.parse_string(data, escaped_text)
assert expected == result
html_text = pg.Many(
pg.Words(
pg.Words.letters+"</>"))
escaped_text = pg.NamedPattern(
'escaped_text',
pg.Escaped(html_text))
expected = [
'escaped_text',
"<p>Some Text</p>"]
result = pg.parse_string(data, escaped_text)
assert expected == result
def document():
return pg.AllOf(
pg.Optional(pg.Ignore(newlines_or_eof)), pg.Optional(doctype),
pg.OneOf(
extends,
pg.Many(
pg.AllOf(pg.OneOf(element, code_block, comment),
pg.Optional(pg.Ignore(pg.Many("\n")))))))
def nested_list():
return pg.AllOf(
pg.Ignore(
pg.Optional(
pg.Many("\n"))),
pg.Indented(
pg.AllOf(
list_item,
pg.Optional(
pg.Many(
list_item,
nested_list))),
optional=True))
def test_parse_many():
emphasis = pg.NamedPattern(
'emphasis',
pg.AllOf(
pg.Ignore("*"),
pg.Words(),
pg.Ignore("*")))
words = pg.NamedPattern(
'words',
pg.Words())
phrase = pg.NamedPattern(
'phrase',
pg.OneOf(
words,
emphasis))
body = pg.NamedPattern(
'body',
pg.Many(phrase))
expected = ['body',
['phrase',
['words', 'a phrase with ']],
['phrase',
['emphasis', "bold words"]],
['phrase',
['words', " in it"]]]
result = pg.parse_string("a phrase with *bold words* in it", body)
assert result == expected
with py.test.raises(pg.NoPatternFound):
result = pg.parse_string("123", body)
def test_indented_bullet():
paragraph = pg.NamedPattern(
'paragraph',
pg.AllOf(
pg.Ignore(pg.Optional("\n")),
pg.Words()))
indented_paragraphs = pg.Indented(
pg.Many(paragraph),
initial_indent="* ")
data = """
* Paragraph One
Paragraph Two
""".strip()
expected = [
'indented_paragraphs',
['paragraph',
"Paragraph One"],
['paragraph',
"Paragraph Two"]]
match, rest = indented_paragraphs(data, "indented_paragraphs")
assert match == expected
def test_match_indented_nested_bullets():
bullet = pg.NamedPattern(
'bullet',
pg.AllOf(
pg.Ignore(
pg.Optional(
pg.Many("\n"))),
pg.Ignore("* "),
pg.Words()))
@pg.lazy
def indented_bullets():
return pg.Indented(
pg.AllOf(
bullet,
pg.Optional(
indented_bullets)),
optional=True)
data = """
* Line One
* Line Two
"""
expected = [
'indented_bullets',
['bullet', "Line One"],
['indented_bullets',
['bullet', "Line Two"]]]
match, rest = indented_bullets(data, 'indented_bullets')
assert match == expected
assert rest == "\n"
def test_with_indent_chars(self):
"Test that Indented can match with indents other than whitespace"
lines = pg.Many(
pg.OneOf(
pg.Words(),
pg.Text("\n")))
indented_text = pg.Indented(
lines,
indent_pattern="> ")
data = """
> Some text
> indented with
> non whitespace
""".strip()
expected = ['indented_text',
"Some text",
"\n",
"indented with",
"\n",
"non whitespace"]
match, rest = indented_text(data, 'indented_text')
assert match == expected
assert rest == ""
def link_text():
return pg.AllOf(
pg.Ignore("["),
pg.Join(
pg.Many(
pg.Not("]"))),
pg.Ignore("]"))
def test_match_many_specificty():
letter_a = pg.NamedPattern(
'letter_a',
"a")
letter_b = pg.NamedPattern(
'letter_b',
"b")
other_letters = pg.NamedPattern(
'other_letters',
pg.Words())
match_letters = pg.Many(
letter_a,
letter_b,
other_letters)
data = "abac"
expected = [
'match_letters',
['letter_a', "a"],
['letter_b', "b"],
['letter_a', "a"],
['other_letters', "c"]]
match, rest = match_letters(data, 'match_letters')
assert match == expected
assert rest == ""
def link_url():
return pg.AllOf(
pg.Ignore("("),
pg.Join(
pg.Many(
pg.Not(")"))),
pg.Ignore(")"))
def code():
return pg.AllOf(
pg.Ignore("`"),
pg.Join(
pg.Many(
pg.Not("`"))),
pg.Ignore("`"))
def test_match_many_simple():
a = pg.NamedPattern(
'a',
"a")
b = pg.NamedPattern(
'b',
"b")
letters = pg.Many(a, b)
expected = ['letters', ['a', "a"], ['b', "b"], ['a', "a"], ['b', "b"]]
match, rest = letters("abab", "letters")
assert match == expected
assert rest == ""
match, rest = letters("ababcc", "letters")
assert match == ['letters', ['a', "a"], ['b', "b"], ['a', "a"], ['b', "b"]]
assert rest == "cc"
match, rest = letters("ababcc", "")
assert match == ['', ['a', "a"], ['b', "b"], ['a', "a"], ['b', "b"]]
assert rest == "cc"
with py.test.raises(pg.NoPatternFound):
match, rest = letters("cab", "letters")
def test_match_one_of():
asterix = pg.Ignore("*")
emphasis = pg.AllOf(
asterix,
pg.Many(pg.Not("*")),
asterix)
phrase = pg.OneOf(
pg.Words(),
emphasis)
expected = ['phrase', "b", "o", "l", "d"]
match, rest = phrase("*bold*", "phrase")
assert match == expected
assert rest == ""
with py.test.raises(pg.NoPatternFound):
match, rest = phrase("123", "phrase")
match, rest = phrase("text", "phrase")
assert match == ['phrase', "text"]
assert rest == ""
# Test match with no name
match, rest = phrase("text", "")
assert match == ['', "text"]
assert rest == ""
def attribute_list():
return pg.AllOf(
pg.Ignore("("), attribute,
pg.Optional(
pg.Many(
pg.AllOf(pg.Ignore(","), pg.Ignore(pg.Optional(" ")),
attribute))), pg.Ignore(")"))
def test_reprs():
# Pattern matchers
assert repr(pg.Some("a")) == "<Some pattern='a'>"
assert repr(pg.Ignore("#")) == "<Ignore pattern=<Text pattern='#'>>"
assert repr(pg.Not("#")) == "<Not pattern=<Text pattern='#'>>"
assert repr(pg.Optional("#")) == "<Optional pattern=<Text pattern='#'>>"
# Option matchers
assert repr(pg.OneOf("abc", pg.Not("#"))) == "<OneOf options=(<Text pattern='abc'>, <Not pattern=<Text pattern='#'>>)>"
assert repr(pg.Many("abc", pg.Not("#"))) == "<Many options=(<Text pattern='abc'>, <Not pattern=<Text pattern='#'>>)>"
assert repr(pg.Words()) == "<Words letters='ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz .,'>"
def body():
return pg.Many(
linebreaks,
horizontal_rule,
title_level_2,
title_level_1,
ordered_list,
unordered_list,
code_block,
paragraph,
blockquote,
)
def test_match_many_empty():
"Test that empty matches don't raise NoPatternFound"
linebreaks = pg.Many(
pg.OneOf(
pg.Ignore(
"\n")))
data = "\n\n"
expected = ['linebreaks', ""]
match, rest = linebreaks(data, 'linebreaks')
assert match == expected
assert rest == ""
def horizontal_rule():
return pg.AllOf(
pg.OneOf(
"---",
"___",
"***",
"- - -",
"_ _ _",
"* * *"),
pg.Optional(
pg.Ignore(
pg.Many(
pg.Not("\n")))))
def _unordered_list_template(bullet_type, spacing):
return pg.Indented(
pg.AllOf(
bullet_type,
pg.Many(
pg.AllOf(
pg.Ignore(
spacing),
pg.OneOf(
bullet_type,
unordered_list,
ordered_list)))),
optional=True)
def test_with_optional(self):
"""Test that optional allows you to match without an indent"""
def list_item():
return pg.AllOf(pg.Ignore("* "), pg.Words())
indented_bullets = pg.Indented(pg.Many(list_item), optional=True)
data = """* A bullet"""
expected = ['indented_bullets', ['list_item', "A bullet"]]
match, rest = pg.match_indented(data, indented_bullets,
'indented_bullets')
assert match == expected
assert rest == ""
def test_without_optional(self):
"""Test that without optional, no match is made"""
def list_item():
return (pg.Ignore("\n* "), pg.Words())
indented_bullets = pg.Indented(pg.Many(list_item))
data = """
* A bullet"""
expected = ['list_item', "A bullet"]
with py.test.raises(pg.NoPatternFound):
match, rest = pg.match_indented(data, indented_bullets,
'indented_bullets')
def test_match_join():
three_times_a = pg.Join(pg.CountOf(3, "a"))
data = "aaa"
expected = ['three_times_a', "aaa"]
match, rest = pg.match_join(data, three_times_a, 'three_times_a')
assert match == expected
assert rest == ""
not_d = pg.Join(pg.Many(pg.Not("d")))
data = "abcd"
expected = ['not_d', "abc"]
match, rest = pg.match_join(data, not_d, 'not_d')
assert match == expected
assert rest == "d"
def test_match_many_complex():
def emphasis():
return pg.AllOf(lambda: pg.Ignore("*"), lambda: pg.Words(),
lambda: pg.Ignore("*"))
def words():
return pg.Words()
body = pg.Many(emphasis, words)
expected = [
'body', ['words', 'a phrase with '], ['emphasis', "bold words"],
['words', " in it"]
]
match, rest = pg.match_many("a phrase with *bold words* in it", body,
'body')
assert match == expected
assert rest == ""
def test_match_escaped():
html_text = pg.NamedPattern(
'html_text',
pg.Many(
pg.Words(
pg.Words.letters + "</>")))
escaped_text = pg.Escaped(html_text)
data = """<p>Some text</p>"""
expected = [
'escaped_text',
['html_text', "<p>Some text</p>"]]
match, rest = escaped_text(data, 'escaped_text')
assert match == expected
assert rest == ""
def numbered_bullet_with_paragraph():
return pg.Indented(
pg.AllOf(
paragraph,
pg.Optional(
pg.AllOf(
linebreaks,
paragraph))),
initial_indent=pg.AllOf(
pg.Optional(
linebreaks),
pg.OneOf(
pg.AllOf(
pg.Ignore(digits),
pg.Ignore("."),
pg.Many('\t')),
pg.AllOf(
digits,
".",
" "))))
def test_with_optional(self):
"""Test that optional allows you to match without an indent"""
list_item = pg.NamedPattern(
'list_item',
pg.AllOf(
pg.Ignore("* "),
pg.Words()))
indented_bullets = pg.Indented(
pg.Many(list_item),
optional=True)
data = """* A bullet"""
expected = [
'indented_bullets',
['list_item', "A bullet"]]
match, rest = indented_bullets(data, 'indented_bullets')
assert match == expected
assert rest == ""
def test_match_many_specificty():
def lettter_a():
return "a"
def lettter_b():
return "b"
def other_letters():
return pg.Words()
match_letters = pg.Many(lettter_a, lettter_b, other_letters)
data = "abac"
expected = [
'match_letters', ['lettter_a', "a"], ['lettter_b', "b"],
['lettter_a', "a"], ['other_letters', "c"]
]
match, rest = pg.match_many(data, match_letters, 'match_letters')
assert match == expected
assert rest == ""
def test_match_many_complex():
emphasis = pg.NamedPattern(
'emphasis',
pg.AllOf(
pg.Ignore("*"),
pg.Words(),
pg.Ignore("*")))
words = pg.NamedPattern(
'words',
pg.Words())
body = pg.Many(emphasis, words)
expected = [
'body',
['words', 'a phrase with '],
['emphasis', "bold words"],
['words', " in it"]]
match, rest = body("a phrase with *bold words* in it", 'body')
assert match == expected
assert rest == ""
def test_match_many_simple():
def a():
return "a"
def b():
return "b"
letters = pg.Many(a, b)
expected = ['letters', ['a', "a"], ['b', "b"], ['a', "a"], ['b', "b"]]
match, rest = pg.match_many("abab", letters, "letters")
assert match == expected
assert rest == ""
match, rest = pg.match_many("ababcc", letters, "letters")
assert match == ['letters', ['a', "a"], ['b', "b"], ['a', "a"], ['b', "b"]]
assert rest == "cc"
match, rest = pg.match_many("ababcc", letters, "")
assert match == ['', ['a', "a"], ['b', "b"], ['a', "a"], ['b', "b"]]
assert rest == "cc"
with py.test.raises(pg.NoPatternFound):
match, rest = pg.match_many("cab", letters, "letters")
