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 test_match_one_of_empty():
b1 = pg.Ignore("*")
b2 = pg.Ignore("-")
bullet = pg.OneOf(b1, b2)
data = "*"
expected = ['bullet', ""]
match, rest = pg.match_one_of(data, bullet, 'bullet')
assert match == expected
assert rest == ""
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 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 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 ordered_list_nested():
return pg.OneOf(
_ordered_list_without_paragraphs_nested,
_ordered_list_with_paragraphs_nested,
_ordered_list_with_single_bullet_nested,
)
def ordered_list():
return pg.OneOf(
_ordered_list_without_paragraphs,
_ordered_list_with_paragraphs,
_ordered_list_with_single_bullet
)
def quoted_string():
return pg.OneOf(
pg.AllOf(pg.Ignore("'"), pg.Optional(pg.Join(pg.Many(pg.Not("'")))),
pg.Ignore("'")),
pg.AllOf(pg.Ignore('"'), pg.Optional(pg.Join(pg.Many(pg.Not('"')))),
pg.Ignore('"')))
def open_tag():
return pg.AllOf(
alphanumerics,
pg.Optional(pg.Many(pg.OneOf(tag_id, tag_class, attribute_list))),
pg.Optional(pg.OneOf(content, code)))
def linebreaks():
return pg.Many(pg.OneOf(pg.Ignore("\n")))
def extends():
return pg.AllOf(pg.Ignore("extends"), pg.Ignore(" "), filename_parts,
pg.Ignore(newlines_or_eof),
pg.Optional(pg.Many(pg.OneOf(replace, append))))
def nested_elements():
return pg.AllOf(
pg.Indented(
pg.Many(pg.OneOf(block, code_block, element, comment, text))),
pg.Ignore(newlines_or_eof))
def content():
return pg.AllOf(pg.Ignore(pg.OneOf(" | ", " ")),
pg.Join(pg.Many(pg.Not(newline_or_eof))))
def attribute():
return pg.OneOf(
pg.AllOf(identifier_parts, pg.Ignore("="),
pg.OneOf(quoted_string, attribute_value_code)), alphanumerics)
def attribute_value_code():
return pg.OneOf(
pg.AllOf(pg.Ignore("{{"), pg.Join(pg.Many(pg.Not("}}"))),
pg.Ignore("}}")), identifier_parts)
def phrase():
return pg.OneOf(words, emphasis)
import lxml
import wiseguy.html
import pegger as pg
from pegger import lazy
alphabet = pg.Words(string.lowercase + string.uppercase)
alphanumerics = pg.Words(string.lowercase + string.uppercase + string.digits)
identifier_parts = pg.Words(string.lowercase + string.uppercase +
string.digits + "-_")
filename_parts = pg.Words(string.lowercase + string.uppercase + string.digits +
"-_.")
whitespace = pg.Words(" \t")
newline_or_eof = pg.OneOf("\n", pg.EOF())
newlines_or_eof = pg.OneOf(pg.Many("\n"), pg.EOF())
@lazy
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")))))))
@lazy