def createLexers(self):
lex = {}
lex['.c'] = CFamilyLexer()
lex['.h'] = CFamilyLexer()
lex['.cpp'] = CppLexer()
lex['.hpp'] = CppLexer()
lex['.css'] = CssLexer()
lex['.sass'] = SassLexer()
lex['.yaml'] = YamlLexer()
lex['.yml'] = YamlLexer()
lex['.json'] = JsonLexer()
lex['.cs'] = CSharpLexer()
lex['.fs'] = FSharpLexer()
lex['.e'] = EiffelLexer()
lex['.erl'] = ErlangLexer()
lex['.hrl'] = ErlangLexer()
lex['.es'] = ErlangLexer()
lex['.f03'] = FortranLexer()
lex['.f90'] = FortranLexer()
lex['.F03'] = FortranLexer()
lex['.F90'] = FortranLexer()
lex['.go'] = GoLexer()
lex['.hs'] = HaskellLexer()
lex['.v'] = VerilogLexer()
lex['.vhdl'] = VhdlLexer()
lex['.vhd'] = VhdlLexer()
lex['.html'] = HtmlLexer()
lex['.htm'] = HtmlLexer()
lex['.xhtml'] = HtmlLexer()
lex['.xml'] = XmlLexer()
lex['.js'] = JavascriptLexer()
lex['.tex'] = TypeScriptLexer()
lex['.coffee'] = CoffeeScriptLexer()
lex['.java'] = JavaLexer()
lex['.scala'] = ScalaLexer()
lex['.kt'] = KotlinLexer()
lex['.ktm'] = KotlinLexer()
lex['.kts'] = KotlinLexer()
lex['.lisp'] = CommonLispLexer()
lex['make'] = MakefileLexer()
lex['Make'] = MakefileLexer()
lex['CMake'] = CMakeLexer()
lex['cmake'] = CMakeLexer()
lex['.m'] = MatlabLexer()
lex['.mat'] = MatlabLexer()
lex['.dpr'] = DelphiLexer()
lex['.perl'] = PerlLexer()
lex['.php'] = PhpLexer()
lex['.pr'] = PrologLexer()
lex['.py'] = Python3Lexer()
lex['.rb'] = RubyLexer()
lex['.sh'] = BashLexer()
lex['.sql'] = MySqlLexer()
lex['.mysql'] = MySqlLexer()
lex['.tcl'] = TclLexer()
lex['.awk'] = AwkLexer()
return lex
def test_can_analyze_text():
mysql_lexer = MySqlLexer()
sql_lexer = SqlLexer()
tsql_lexer = TransactSqlLexer()
code_to_expected_lexer_map = {
'select `a`, `bc` from some': mysql_lexer,
'select a, bc from some': sql_lexer,
'select [a], [bc] from some': tsql_lexer,
'-- `a`, `bc`\nselect [a], [bc] from some': tsql_lexer,
'-- `a`, `bc`\nselect [a], [bc] from some; go': tsql_lexer,
}
sql_lexers = set(code_to_expected_lexer_map.values())
for code, expected_lexer in code_to_expected_lexer_map.items():
ratings_and_lexers = list((lexer.analyse_text(code), lexer.name) for lexer in sql_lexers)
best_rating, best_lexer_name = sorted(ratings_and_lexers, reverse=True)[0]
expected_rating = expected_lexer.analyse_text(code)
message = (
'lexer must be %s (rating %.2f) instead of '
'%s (rating %.2f) for analyse_text() on code:\n%s') % (
expected_lexer.name,
expected_rating,
best_lexer_name,
best_rating,
code
)
assert expected_lexer.name == best_lexer_name, message
def highlight(text):
# Generated HTML contains unnecessary newline at the end
# before </pre> closing tag.
# We need to remove that newline because it's screwing up
# QTextEdit formatting and is being displayed
# as a non-editable whitespace.
# However, origin solution works wired for \n at start and end
# I add flag \b, which is invisible
text = '\b' + text + '\b'
highlighted_text = _highlight(text, MySqlLexer(), HtmlFormatter())
# Split generated HTML by last newline in it
# argument 1 indicates that we only want to split the string
# by one specified delimiter from the right.
parts = highlighted_text.rsplit("\n", 1)
# Glue back 2 split parts to get the HTML without last
# unnecessary newline
highlighted_text_no_last_newline = "".join(parts)
return highlighted_text_no_last_newline.replace('\b', '')
def lexer():
yield MySqlLexer()
# Re-write index.html so that the code block comments are replaced by the
# Pygment-ized code.
blocks = get_blocks()
with codecs.open('index-src.html', 'r', 'utf-8') as fi:
with codecs.open('index.html', 'w', 'utf-8') as fo:
for line in fi:
line_els = line.strip().split()
if len(line_els) > 1 and line_els[1] == 'code-block:':
block_name = line_els[2]
if block_name in blocks:
block = blocks[block_name]['block']
lang = blocks[block_name]['lang']
if lang == 'python':
lexer = PythonLexer()
formatter = pyformatter
elif lang == 'shell':
lexer = BashLexer()
formatter = shformatter
elif lang == 'sql':
lexer = MySqlLexer()
formatter = sqlformatter
elif lang == 'ini':
lexer = IniLexer()
formatter = iniformatter
else:
lexer = JsonLexer()
formatter = jsonformatter
fo.write(highlight(block, lexer, formatter))
else:
fo.write(line)
pass
if extens == "py" or extens == "pyw" or extens == "sc" or extens == "sage" or extens == "tac":
ui_core = CoreUI(lexer=PythonLexer())
elif extens == "txt" or extens == "README" or extens == "text":
ui_core = CoreUI(lexer=TextLexer())
elif extens == "htm" or extens == "html" or extens == "css" or extens == "js" or extens == "md":
ui_core = CoreUI(lexer=HtmlLexer())
elif extens == "xml" or extens == "xsl" or extens == "rss" or extens == "xslt" or extens == "xsd" or extens == "wsdl" or extens == "wsf":
ui_core = CoreUI(lexer=XmlLexer())
elif extens == "php" or extens == "php5":
ui_core = CoreUI(lexer=HtmlPhpLexer())
elif extens == "pl" or extens == "pm" or extens == "nqp" or extens == "p6" or extens == "6pl" or extens == "p6l" or extens == "pl6" or extens == "pm" or extens == "p6m" or extens == "pm6" or extens == "t":
ui_core = CoreUI(lexer=Perl6Lexer())
elif extens == "rb" or extens == "rbw" or extens == "rake" or extens == "rbx" or extens == "duby" or extens == "gemspec":
ui_core = CoreUI(lexer=RubyLexer())
elif extens == "ini" or extens == "init":
ui_core = CoreUI(lexer=IniLexer())
elif extens == "conf" or extens == "cnf" or extens == "config":
ui_core = CoreUI(lexer=ApacheConfLexer())
elif extens == "sh" or extens == "cmd" or extens == "bashrc" or extens == "bash_profile":
ui_core = CoreUI(lexer=BashLexer())
elif extens == "diff" or extens == "patch":
ui_core = CoreUI(lexer=DiffLexer())
elif extens == "cs":
ui_core = CoreUI(lexer=CSharpLexer())
elif extens == "sql":
ui_core = CoreUI(lexer=MySqlLexer())
else:
ui_core = CoreUI(lexer=PythonLexer()) # default (no extension) lexer is python
ui_core.mainloop()
