diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-04 11:33:32 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-04 11:33:32 +0000 |
commit | 1f403ad2197fc7442409f434ee574f3e6b46fb73 (patch) | |
tree | 0299c6dd11d5edfa918a29b6456bc1875f1d288c /tests/test_markdown_lexer.py | |
parent | Initial commit. (diff) | |
download | pygments-1f403ad2197fc7442409f434ee574f3e6b46fb73.tar.xz pygments-1f403ad2197fc7442409f434ee574f3e6b46fb73.zip |
Adding upstream version 2.14.0+dfsg.upstream/2.14.0+dfsgupstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'tests/test_markdown_lexer.py')
-rw-r--r-- | tests/test_markdown_lexer.py | 178 |
1 files changed, 178 insertions, 0 deletions
diff --git a/tests/test_markdown_lexer.py b/tests/test_markdown_lexer.py new file mode 100644 index 0000000..46b2911 --- /dev/null +++ b/tests/test_markdown_lexer.py @@ -0,0 +1,178 @@ +""" + Pygments Markdown lexer tests + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + :copyright: Copyright 2006-2022 by the Pygments team, see AUTHORS. + :license: BSD, see LICENSE for details. +""" + +import pytest +from pygments.token import Generic, Token, String + +from pygments.lexers.markup import MarkdownLexer + + +@pytest.fixture(scope='module') +def lexer(): + yield MarkdownLexer() + + +def assert_same_text(lexer, text): + """Show that lexed markdown does not remove any content. """ + tokens = list(lexer.get_tokens_unprocessed(text)) + output = ''.join(t[2] for t in tokens) + assert text == output + + +def test_code_fence(lexer): + assert_same_text(lexer, r'```\nfoo\n```\n') + + +def test_code_fence_gsm(lexer): + assert_same_text(lexer, r'```markdown\nfoo\n```\n') + + +def test_code_fence_gsm_with_no_lexer(lexer): + assert_same_text(lexer, r'```invalid-lexer\nfoo\n```\n') + + +def test_invalid_atx_heading(lexer): + fragments = ( + '#', + 'a #', + '*#', + ) + + for fragment in fragments: + for token, _ in lexer.get_tokens(fragment): + assert token != Generic.Heading + + +def test_atx_heading(lexer): + fragments = ( + '#Heading', + '# Heading', + '# Another heading', + '# Another # heading', + '# Heading #', + ) + + for fragment in fragments: + tokens = [ + (Generic.Heading, fragment), + (Token.Text, '\n'), + ] + assert list(lexer.get_tokens(fragment)) == tokens + + +def test_invalid_atx_subheading(lexer): + fragments = ( + '##', + 'a ##', + '*##', + '####### too many hashes' + ) + + for fragment in fragments: + for token, _ in lexer.get_tokens(fragment): + assert token != Generic.Subheading + + +def test_atx_subheading(lexer): + fragments = ( + '##Subheading', + '## Subheading', + '### Subheading', + '#### Subheading', + '##### Subheading', + '###### Subheading', + '## Another subheading', + '## Another ## subheading', + '###### Subheading #', + '###### Subheading ######', + ) + + for fragment in fragments: + tokens = [ + (Generic.Subheading, fragment), + (Token.Text, '\n'), + ] + assert list(lexer.get_tokens(fragment)) == tokens + + +def test_invalid_setext_heading(lexer): + fragments = ( + 'Heading\n', + 'Heading\n_', + 'Heading\n =====', + 'Heading\na=====', + '=====', + '\n=\n', + 'Heading\n=====Text' + ) + + for fragment in fragments: + for token, _ in lexer.get_tokens(fragment): + assert token != Generic.Heading + + +def test_setext_heading(lexer): + fragments = ( + 'Heading\n=', + 'Heading\n=======', + 'Heading\n==========', + ) + + for fragment in fragments: + tokens = [ + (Generic.Heading, fragment.split('\n')[0]), + (Token.Text, '\n'), + (Generic.Heading, fragment.split('\n')[1]), + (Token.Text, '\n'), + ] + assert list(lexer.get_tokens(fragment)) == tokens + + +def test_invalid_setext_subheading(lexer): + fragments = ( + 'Subheading\n', + 'Subheading\n_', + 'Subheading\n -----', + 'Subheading\na-----', + '-----', + '\n-\n', + 'Subheading\n-----Text' + ) + + for fragment in fragments: + for token, _ in lexer.get_tokens(fragment): + assert token != Generic.Subheading + + +def test_setext_subheading(lexer): + fragments = ( + 'Subheading\n-', + 'Subheading\n----------', + 'Subheading\n-----------', + ) + + for fragment in fragments: + tokens = [ + (Generic.Subheading, fragment.split('\n')[0]), + (Token.Text, '\n'), + (Generic.Subheading, fragment.split('\n')[1]), + (Token.Text, '\n'), + ] + assert list(lexer.get_tokens(fragment)) == tokens + + +def test_invalid_code_block(lexer): + fragments = ( + '```code```', + 'prefix not allowed before ```\ncode block\n```' + ' code', + ) + + for fragment in fragments: + for token, _ in lexer.get_tokens(fragment): + assert token != String.Backtick |