diff options
Diffstat (limited to 'pygments')
| -rw-r--r-- | pygments/cmdline.py | 2 | ||||
| -rw-r--r-- | pygments/lexer.py | 4 | ||||
| -rw-r--r-- | pygments/lexers/_stan_builtins.py | 111 | ||||
| -rw-r--r-- | pygments/lexers/agile.py | 6 | ||||
| -rw-r--r-- | pygments/lexers/asm.py | 20 | ||||
| -rw-r--r-- | pygments/lexers/jvm.py | 144 | ||||
| -rw-r--r-- | pygments/lexers/math.py | 8 | ||||
| -rw-r--r-- | pygments/lexers/other.py | 42 | ||||
| -rw-r--r-- | pygments/lexers/web.py | 10 | ||||
| -rw-r--r-- | pygments/styles/monokai.py | 6 |
10 files changed, 216 insertions, 137 deletions
diff --git a/pygments/cmdline.py b/pygments/cmdline.py index c25204bf..f260f76a 100644 --- a/pygments/cmdline.py +++ b/pygments/cmdline.py @@ -92,7 +92,7 @@ def _parse_options(o_strs): for o_arg in o_args: o_arg = o_arg.strip() try: - o_key, o_val = o_arg.split('=') + o_key, o_val = o_arg.split('=', 1) o_key = o_key.strip() o_val = o_val.strip() except ValueError: diff --git a/pygments/lexer.py b/pygments/lexer.py index 662c059e..8538fe7c 100644 --- a/pygments/lexer.py +++ b/pygments/lexer.py @@ -192,7 +192,9 @@ class Lexer(object): def get_tokens_unprocessed(self, text): """ - Return an iterable of (tokentype, value) pairs. + Return an iterable of (index, tokentype, value) pairs where "index" + is the starting position of the token within the input text. + In subclasses, implement this method as a generator to maximize effectiveness. """ diff --git a/pygments/lexers/_stan_builtins.py b/pygments/lexers/_stan_builtins.py index 637072e4..1cea6ba4 100644 --- a/pygments/lexers/_stan_builtins.py +++ b/pygments/lexers/_stan_builtins.py @@ -10,9 +10,10 @@ This file contains the names of functions for Stan used by :license: BSD, see LICENSE for details. """ -KEYWORDS = ['else', 'for', 'if', 'in', 'lower', 'lp__', 'print', 'upper', 'while'] +KEYWORDS = ['else', 'for', 'if', 'in', 'lp__', 'print', 'while'] -TYPES = [ 'corr_matrix', +TYPES = [ 'cholesky_factor_cov', + 'corr_matrix', 'cov_matrix', 'int', 'matrix', @@ -34,35 +35,53 @@ FUNCTIONS = [ 'Phi', 'atan', 'atan2', 'atanh', + 'bernoulli_ccdf_log', 'bernoulli_cdf', + 'bernoulli_cdf_log', 'bernoulli_log', 'bernoulli_logit_log', 'bernoulli_rng', + 'bessel_first_kind', + 'bessel_second_kind', + 'beta_binomial_ccdf_log', 'beta_binomial_cdf', + 'beta_binomial_cdf_log', 'beta_binomial_log', 'beta_binomial_rng', + 'beta_ccdf_log', 'beta_cdf', + 'beta_cdf_log', 'beta_log', 'beta_rng', 'binary_log_loss', + 'binomial_ccdf_log', 'binomial_cdf', + 'binomial_cdf_log', 'binomial_coefficient_log', 'binomial_log', 'binomial_logit_log', 'binomial_rng', 'block', 'categorical_log', + 'categorical_logit_log', 'categorical_rng', + 'cauchy_ccdf_log', 'cauchy_cdf', + 'cauchy_cdf_log', 'cauchy_log', 'cauchy_rng', 'cbrt', 'ceil', + 'chi_square_ccdf_log', + 'chi_square_cdf', + 'chi_square_cdf_log', 'chi_square_log', 'chi_square_rng', 'cholesky_decompose', 'col', 'cols', + 'columns_dot_product', + 'columns_dot_self', 'cos', 'cosh', 'crossprod', @@ -77,55 +96,78 @@ FUNCTIONS = [ 'Phi', 'dirichlet_rng', 'dot_product', 'dot_self', + 'double_exponential_ccdf_log', + 'double_exponential_cdf', + 'double_exponential_cdf_log', 'double_exponential_log', 'double_exponential_rng', 'e', 'eigenvalues_sym', 'eigenvectors_sym', - 'epsilon', 'erf', 'erfc', 'exp', 'exp2', + 'exp_mod_normal_ccdf_log', 'exp_mod_normal_cdf', + 'exp_mod_normal_cdf_log', 'exp_mod_normal_log', 'exp_mod_normal_rng', 'expm1', + 'exponential_ccdf_log', 'exponential_cdf', + 'exponential_cdf_log', 'exponential_log', 'exponential_rng', 'fabs', + 'falling_factorial', 'fdim', 'floor', 'fma', 'fmax', 'fmin', 'fmod', + 'gamma_ccdf_log', + 'gamma_cdf', + 'gamma_cdf_log', 'gamma_log', + 'gamma_p', + 'gamma_q', 'gamma_rng', + 'gaussian_dlm_obs_log', + 'gumbel_ccdf_log', 'gumbel_cdf', + 'gumbel_cdf_log', 'gumbel_log', 'gumbel_rng', + 'head', 'hypergeometric_log', 'hypergeometric_rng', 'hypot', 'if_else', + 'increment_log_prob', 'int_step', + 'inv', + 'inv_chi_square_ccdf_log', 'inv_chi_square_cdf', + 'inv_chi_square_cdf_log', 'inv_chi_square_log', 'inv_chi_square_rng', 'inv_cloglog', + 'inv_gamma_ccdf_log', 'inv_gamma_cdf', + 'inv_gamma_cdf_log', 'inv_gamma_log', 'inv_gamma_rng', 'inv_logit', + 'inv_sqrt', + 'inv_square', 'inv_wishart_log', 'inv_wishart_rng', 'inverse', + 'inverse_spd', 'lbeta', 'lgamma', - 'lkj_corr_cholesky_log', - 'lkj_corr_cholesky_rng', 'lkj_corr_log', 'lkj_corr_rng', 'lkj_cov_log', @@ -133,96 +175,145 @@ FUNCTIONS = [ 'Phi', 'log', 'log10', 'log1m', + 'log1m_exp', 'log1m_inv_logit', 'log1p', 'log1p_exp', 'log2', 'log_determinant', + 'log_diff_exp', + 'log_falling_factorial', 'log_inv_logit', + 'log_rising_factorial', + 'log_softmax', 'log_sum_exp', + 'logistic_ccdf_log', 'logistic_cdf', + 'logistic_cdf_log', 'logistic_log', 'logistic_rng', 'logit', + 'lognormal_ccdf_log', 'lognormal_cdf', + 'lognormal_cdf_log', 'lognormal_log', 'lognormal_rng', + 'machine_precision', 'max', 'mdivide_left_tri_low', 'mdivide_right_tri_low', 'mean', 'min', + 'modified_bessel_first_kind', + 'modified_bessel_second_kind', 'multi_normal_cholesky_log', 'multi_normal_log', 'multi_normal_prec_log', 'multi_normal_rng', 'multi_student_t_log', 'multi_student_t_rng', - 'multinomial_cdf', 'multinomial_log', 'multinomial_rng', 'multiply_log', 'multiply_lower_tri_self_transpose', + 'neg_binomial_ccdf_log', 'neg_binomial_cdf', + 'neg_binomial_cdf_log', 'neg_binomial_log', 'neg_binomial_rng', - 'negative_epsilon', 'negative_infinity', + 'normal_ccdf_log', 'normal_cdf', + 'normal_cdf_log', 'normal_log', 'normal_rng', 'not_a_number', 'ordered_logistic_log', 'ordered_logistic_rng', 'owens_t', + 'pareto_ccdf_log', 'pareto_cdf', + 'pareto_cdf_log', 'pareto_log', 'pareto_rng', 'pi', + 'poisson_ccdf_log', 'poisson_cdf', + 'poisson_cdf_log', 'poisson_log', 'poisson_log_log', 'poisson_rng', 'positive_infinity', 'pow', 'prod', + 'quad_form', + 'rank', + 'rayleigh_ccdf_log', + 'rayleigh_cdf', + 'rayleigh_cdf_log', + 'rayleigh_log', + 'rayleigh_rng', 'rep_array', 'rep_matrix', 'rep_row_vector', 'rep_vector', + 'rising_factorial', 'round', 'row', 'rows', + 'rows_dot_product', + 'rows_dot_self', + 'scaled_inv_chi_square_ccdf_log', 'scaled_inv_chi_square_cdf', + 'scaled_inv_chi_square_cdf_log', 'scaled_inv_chi_square_log', 'scaled_inv_chi_square_rng', 'sd', + 'segment', 'sin', 'singular_values', 'sinh', 'size', + 'skew_normal_ccdf_log', 'skew_normal_cdf', + 'skew_normal_cdf_log', 'skew_normal_log', 'skew_normal_rng', 'softmax', + 'sort_asc', + 'sort_desc', 'sqrt', 'sqrt2', 'square', 'step', + 'student_t_ccdf_log', 'student_t_cdf', + 'student_t_cdf_log', 'student_t_log', 'student_t_rng', + 'sub_col', + 'sub_row', 'sum', + 'tail', 'tan', 'tanh', 'tcrossprod', 'tgamma', + 'to_vector', 'trace', + 'trace_gen_quad_form', + 'trace_quad_form', 'trunc', + 'uniform_ccdf_log', + 'uniform_cdf', + 'uniform_cdf_log', 'uniform_log', 'uniform_rng', 'variance', + 'von_mises_log', + 'weibull_ccdf_log', 'weibull_cdf', + 'weibull_cdf_log', 'weibull_log', 'weibull_rng', 'wishart_log', @@ -236,6 +327,7 @@ DISTRIBUTIONS = [ 'bernoulli', 'binomial_coefficient', 'binomial_logit', 'categorical', + 'categorical_logit', 'cauchy', 'chi_square', 'dirichlet', @@ -243,13 +335,13 @@ DISTRIBUTIONS = [ 'bernoulli', 'exp_mod_normal', 'exponential', 'gamma', + 'gaussian_dlm_obs', 'gumbel', 'hypergeometric', 'inv_chi_square', 'inv_gamma', 'inv_wishart', 'lkj_corr', - 'lkj_corr_cholesky', 'lkj_cov', 'logistic', 'lognormal', @@ -265,10 +357,12 @@ DISTRIBUTIONS = [ 'bernoulli', 'pareto', 'poisson', 'poisson_log', + 'rayleigh', 'scaled_inv_chi_square', 'skew_normal', 'student_t', 'uniform', + 'von_mises', 'weibull', 'wishart'] @@ -357,4 +451,3 @@ RESERVED = [ 'alignas', 'wchar_t', 'xor', 'xor_eq'] - diff --git a/pygments/lexers/agile.py b/pygments/lexers/agile.py index 1f81365e..23404320 100644 --- a/pygments/lexers/agile.py +++ b/pygments/lexers/agile.py @@ -532,7 +532,7 @@ class RubyLexer(ExtendedRegexLexer): (r":'(\\\\|\\'|[^'])*'", String.Symbol), (r"'(\\\\|\\'|[^'])*'", String.Single), (r':"', String.Symbol, 'simple-sym'), - (r'([a-zA-Z_][a-zA-Z0-9]*)(:)(?!:)', + (r'([a-zA-Z_][a-zA-Z0-9_]*)(:)(?!:)', bygroups(String.Symbol, Punctuation)), # Since Ruby 1.9 (r'"', String.Double, 'simple-string'), (r'(?<!\.)`', String.Backtick, 'simple-backtick'), @@ -848,7 +848,7 @@ class PerlLexer(RegexLexer): name = 'Perl' aliases = ['perl', 'pl'] - filenames = ['*.pl', '*.pm'] + filenames = ['*.pl', '*.pm', '*.t'] mimetypes = ['text/x-perl', 'application/x-perl'] flags = re.DOTALL | re.MULTILINE @@ -1937,7 +1937,7 @@ class Perl6Lexer(ExtendedRegexLexer): name = 'Perl6' aliases = ['perl6', 'pl6'] filenames = ['*.pl', '*.pm', '*.nqp', '*.p6', '*.6pl', '*.p6l', '*.pl6', - '*.6pm', '*.p6m', '*.pm6'] + '*.6pm', '*.p6m', '*.pm6', '*.t'] mimetypes = ['text/x-perl6', 'application/x-perl6'] flags = re.MULTILINE | re.DOTALL | re.UNICODE diff --git a/pygments/lexers/asm.py b/pygments/lexers/asm.py index 3f67862c..c599deff 100644 --- a/pygments/lexers/asm.py +++ b/pygments/lexers/asm.py @@ -216,6 +216,7 @@ class LlvmLexer(RegexLexer): (r'@' + identifier, Name.Variable.Global),#Name.Identifier.Global), (r'%\d+', Name.Variable.Anonymous),#Name.Identifier.Anonymous), (r'@\d+', Name.Variable.Global),#Name.Identifier.Anonymous), + (r'#\d+', Name.Variable.Global),#Name.Identifier.Global), (r'!' + identifier, Name.Variable), (r'!\d+', Name.Variable.Anonymous), (r'c?' + string, String), @@ -242,17 +243,24 @@ class LlvmLexer(RegexLexer): r'|thread_local|zeroinitializer|undef|null|to|tail|target|triple' r'|datalayout|volatile|nuw|nsw|nnan|ninf|nsz|arcp|fast|exact|inbounds' r'|align|addrspace|section|alias|module|asm|sideeffect|gc|dbg' + r'|linker_private_weak' + r'|attributes|blockaddress|initialexec|localdynamic|localexec' + r'|prefix|unnamed_addr' r'|ccc|fastcc|coldcc|x86_stdcallcc|x86_fastcallcc|arm_apcscc' r'|arm_aapcscc|arm_aapcs_vfpcc|ptx_device|ptx_kernel' + r'|intel_ocl_bicc|msp430_intrcc|spir_func|spir_kernel' + r'|x86_64_sysvcc|x86_64_win64cc|x86_thiscallcc' r'|cc|c' r'|signext|zeroext|inreg|sret|nounwind|noreturn|noalias|nocapture' r'|byval|nest|readnone|readonly' - r'|inlinehint|noinline|alwaysinline|optsize|ssp|sspreq|noredzone' r'|noimplicitfloat|naked' + r'|builtin|cold|nobuiltin|noduplicate|nonlazybind|optnone' + r'|returns_twice|sanitize_address|sanitize_memory|sanitize_thread' + r'|sspstrong|uwtable|returned' r'|type|opaque' @@ -261,24 +269,30 @@ class LlvmLexer(RegexLexer): r'|oeq|one|olt|ogt|ole' r'|oge|ord|uno|ueq|une' r'|x' + r'|acq_rel|acquire|alignstack|atomic|catch|cleanup|filter' + r'|inteldialect|max|min|monotonic|nand|personality|release' + r'|seq_cst|singlethread|umax|umin|unordered|xchg' # instructions r'|add|fadd|sub|fsub|mul|fmul|udiv|sdiv|fdiv|urem|srem|frem|shl' r'|lshr|ashr|and|or|xor|icmp|fcmp' r'|phi|call|trunc|zext|sext|fptrunc|fpext|uitofp|sitofp|fptoui' - r'fptosi|inttoptr|ptrtoint|bitcast|select|va_arg|ret|br|switch' + r'|fptosi|inttoptr|ptrtoint|bitcast|select|va_arg|ret|br|switch' r'|invoke|unwind|unreachable' + r'|indirectbr|landingpad|resume' r'|malloc|alloca|free|load|store|getelementptr' r'|extractelement|insertelement|shufflevector|getresult' r'|extractvalue|insertvalue' + + r'|atomicrmw|cmpxchg|fence' r')\b', Keyword), # Types - (r'void|float|double|x86_fp80|fp128|ppc_fp128|label|metadata', + (r'void|half|float|double|x86_fp80|fp128|ppc_fp128|label|metadata', Keyword.Type), # Integer types diff --git a/pygments/lexers/jvm.py b/pygments/lexers/jvm.py index 8b5d5964..e07656a4 100644 --- a/pygments/lexers/jvm.py +++ b/pygments/lexers/jvm.py @@ -15,7 +15,6 @@ from pygments.lexer import Lexer, RegexLexer, include, bygroups, using, \ this from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ Number, Punctuation -from pygments.util import get_choice_opt from pygments import unistring as uni @@ -937,114 +936,65 @@ class CeylonLexer(RegexLexer): class KotlinLexer(RegexLexer): """ - For `Kotlin <http://confluence.jetbrains.net/display/Kotlin/>`_ + For `Kotlin <http://kotlin.jetbrains.org/>`_ source code. - Additional options accepted: - - `unicodelevel` - Determines which Unicode characters this lexer allows for identifiers. - The possible values are: - - * ``none`` -- only the ASCII letters and numbers are allowed. This - is the fastest selection. - * ``basic`` -- all Unicode characters from the specification except - category ``Lo`` are allowed. - * ``full`` -- all Unicode characters as specified in the C# specs - are allowed. Note that this means a considerable slowdown since the - ``Lo`` category has more than 40,000 characters in it! - - The default value is ``basic``. - *New in Pygments 1.5.* """ name = 'Kotlin' aliases = ['kotlin'] filenames = ['*.kt'] - mimetypes = ['text/x-kotlin'] # inferred + mimetypes = ['text/x-kotlin'] flags = re.MULTILINE | re.DOTALL | re.UNICODE - # for the range of allowed unicode characters in identifiers, - # see http://www.ecma-international.org/publications/files/ECMA-ST/Ecma-334.pdf - - levels = { - 'none': '@?[_a-zA-Z][a-zA-Z0-9_]*', - 'basic': ('@?[_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + ']' + - '[' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + - uni.Nd + uni.Pc + uni.Cf + uni.Mn + uni.Mc + ']*'), - 'full': ('@?(?:_|[^' + - uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl') + '])' - + '[^' + uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl', - 'Nd', 'Pc', 'Cf', 'Mn', 'Mc') + ']*'), - } + kt_name = ('@?[_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + ']' + + '[' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + uni.Nd + + uni.Pc + uni.Cf + uni.Mn + uni.Mc + ']*') + kt_id = '(' + kt_name + '|`' + kt_name + '`)' - tokens = {} - token_variants = True - - for levelname, cs_ident in levels.items(): - tokens[levelname] = { - 'root': [ - # method names - (r'^([ \t]*(?:' + cs_ident + r'(?:\[\])?\s+)+?)' # return type - r'(' + cs_ident + ')' # method name - r'(\s*)(\()', # signature start - bygroups(using(this), Name.Function, Text, Punctuation)), - (r'^\s*\[.*?\]', Name.Attribute), - (r'[^\S\n]+', Text), - (r'\\\n', Text), # line continuation - (r'//.*?\n', Comment.Single), - (r'/[*](.|\n)*?[*]/', Comment.Multiline), - (r'\n', Text), - (r'[~!%^&*()+=|\[\]:;,.<>/?-]', Punctuation), - (r'[{}]', Punctuation), - (r'@"(""|[^"])*"', String), - (r'"(\\\\|\\"|[^"\n])*["\n]', String), - (r"'\\.'|'[^\\]'", String.Char), - (r"[0-9](\.[0-9]*)?([eE][+-][0-9]+)?" - r"[flFLdD]?|0[xX][0-9a-fA-F]+[Ll]?", Number), - (r'#[ \t]*(if|endif|else|elif|define|undef|' - r'line|error|warning|region|endregion|pragma)\b.*?\n', - Comment.Preproc), - (r'\b(extern)(\s+)(alias)\b', bygroups(Keyword, Text, - Keyword)), - (r'(abstract|as|break|catch|' - r'fun|continue|default|delegate|' - r'do|else|enum|extern|false|finally|' - r'fixed|for|goto|if|implicit|in|interface|' - r'internal|is|lock|null|' - r'out|override|private|protected|public|readonly|' - r'ref|return|sealed|sizeof|' - r'when|this|throw|true|try|typeof|' - r'unchecked|unsafe|virtual|void|while|' - r'get|set|new|partial|yield|val|var)\b', Keyword), - (r'(global)(::)', bygroups(Keyword, Punctuation)), - (r'(bool|byte|char|decimal|double|dynamic|float|int|long|' - r'short)\b\??', Keyword.Type), - (r'(class|struct)(\s+)', bygroups(Keyword, Text), 'class'), - (r'(package|using)(\s+)', bygroups(Keyword, Text), 'package'), - (cs_ident, Name), - ], - 'class': [ - (cs_ident, Name.Class, '#pop') - ], - 'package': [ - (r'(?=\()', Text, '#pop'), # using (resource) - ('(' + cs_ident + r'|\.)+', Name.Namespace, '#pop') - ] - } - - def __init__(self, **options): - level = get_choice_opt(options, 'unicodelevel', self.tokens.keys(), - 'basic') - if level not in self._all_tokens: - # compile the regexes now - self._tokens = self.__class__.process_tokendef(level) - else: - self._tokens = self._all_tokens[level] - - RegexLexer.__init__(self, **options) + tokens = { + 'root': [ + (r'^\s*\[.*?\]', Name.Attribute), + (r'[^\S\n]+', Text), + (r'\\\n', Text), # line continuation + (r'//.*?\n', Comment.Single), + (r'/[*].*?[*]/', Comment.Multiline), + (r'\n', Text), + (r'::|!!|\?[:.]', Operator), + (r'[~!%^&*()+=|\[\]:;,.<>/?-]', Punctuation), + (r'[{}]', Punctuation), + (r'@"(""|[^"])*"', String), + (r'"(\\\\|\\"|[^"\n])*["\n]', String), + (r"'\\.'|'[^\\]'", String.Char), + (r"[0-9](\.[0-9]*)?([eE][+-][0-9]+)?[flFL]?|" + r"0[xX][0-9a-fA-F]+[Ll]?", Number), + (r'(class)(\s+)(object)', bygroups(Keyword, Text, Keyword)), + (r'(class|trait|object)(\s+)', bygroups(Keyword, Text), 'class'), + (r'(package|import)(\s+)', bygroups(Keyword, Text), 'package'), + (r'(val|var)(\s+)', bygroups(Keyword, Text), 'property'), + (r'(fun)(\s+)', bygroups(Keyword, Text), 'function'), + (r'(abstract|annotation|as|break|by|catch|class|continue|do|else|' + r'enum|false|final|finally|for|fun|get|if|import|in|inner|' + r'internal|is|null|object|open|out|override|package|private|' + r'protected|public|reified|return|set|super|this|throw|trait|' + r'true|try|type|val|var|vararg|when|where|while|This)\b', Keyword), + (kt_id, Name), + ], + 'package': [ + (r'\S+', Name.Namespace, '#pop') + ], + 'class': [ + (kt_id, Name.Class, '#pop') + ], + 'property': [ + (kt_id, Name.Property, '#pop') + ], + 'function': [ + (kt_id, Name.Function, '#pop') + ], + } class XtendLexer(RegexLexer): diff --git a/pygments/lexers/math.py b/pygments/lexers/math.py index f0e49fef..1cdcfb43 100644 --- a/pygments/lexers/math.py +++ b/pygments/lexers/math.py @@ -167,8 +167,8 @@ class JuliaConsoleLexer(Lexer): if line.startswith('julia>'): insertions.append((len(curcode), - [(0, Generic.Prompt, line[:3])])) - curcode += line[3:] + [(0, Generic.Prompt, line[:6])])) + curcode += line[6:] elif line.startswith(' '): @@ -1308,9 +1308,9 @@ class JagsLexer(RegexLexer): class StanLexer(RegexLexer): """Pygments Lexer for Stan models. - The Stan modeling language is specified in the *Stan 1.3.0 + The Stan modeling language is specified in the *Stan 2.0.1 Modeling Language Manual* `pdf - <http://code.google.com/p/stan/downloads/detail?name=stan-reference-1.3.0.pdf>`_. + <https://github.com/stan-dev/stan/releases/download/v2.0.1/stan-reference-2.0.1.pdf>`__ *New in Pygments 1.6.* """ diff --git a/pygments/lexers/other.py b/pygments/lexers/other.py index 10598fb4..44d7404e 100644 --- a/pygments/lexers/other.py +++ b/pygments/lexers/other.py @@ -1217,15 +1217,16 @@ class ModelicaLexer(RegexLexer): ], 'statements': [ (r'"', String, 'string'), + (r'\'', Name, 'quoted_ident'), (r'(\d+\.\d*|\.\d+|\d+|\d.)[eE][+-]?\d+[lL]?', Number.Float), (r'(\d+\.\d*|\.\d+)', Number.Float), (r'\d+[Ll]?', Number.Integer), (r'[~!%^&*+=|?:<>/-]', Operator), (r'[()\[\]{},.;]', Punctuation), (r'(true|false|NULL|Real|Integer|Boolean)\b', Name.Builtin), - (r"([a-zA-Z_][\w]*|'[a-zA-Z_\+\-\*\/\^][\w]*')" - r"(\.([a-zA-Z_][\w]*|'[a-zA-Z_\+\-\*\/\^][\w]*'))+", Name.Class), - (r"('[\w\+\-\*\/\^]+'|\w+)", Name), + (r'([a-zA-Z_][\w\[\]]*|\'[a-zA-Z_\+\-\*\/\^][\w]*\')' + r'(\.([a-zA-Z_\][\w\[\]]*|\'[a-zA-Z_\+\-\*\/\^][\w]*\'))+', Name.Class), + (r'(\'[\w\+\-\*\/\^]+\'|\w+)', Name), ], 'root': [ include('whitespace'), @@ -1239,7 +1240,7 @@ class ModelicaLexer(RegexLexer): 'keywords': [ (r'(algorithm|annotation|break|connect|constant|constrainedby|' r'discrete|each|else|elseif|elsewhen|encapsulated|enumeration|' - r'end|equation|exit|expandable|extends|' + r'equation|exit|expandable|extends|' r'external|false|final|flow|for|if|import|impure|in|initial\sequation|' r'inner|input|loop|nondiscrete|outer|output|parameter|partial|' r'protected|public|pure|redeclare|replaceable|stream|time|then|true|' @@ -1258,9 +1259,13 @@ class ModelicaLexer(RegexLexer): r'terminate)\b', Name.Builtin), ], 'classes': [ - (r'(block|class|connector|function|model|package|' - r'record|type)(\s+)([A-Za-z_]+)', - bygroups(Keyword, Text, Name.Class)) + (r'(block|class|connector|end|function|model|package|' + r'record|type)(\s+)((?!if|when|while)[A-Za-z_]\w*|[\'][^\']+[\'])([;]?)', + bygroups(Keyword, Text, Name.Class, Text)) + ], + 'quoted_ident': [ + (r'\'', Name, '#pop'), + (r'[^\']+', Name), # all other characters ], 'string': [ (r'"', String, '#pop'), @@ -1271,7 +1276,7 @@ class ModelicaLexer(RegexLexer): (r'\\', String), # stray backslash ], 'html-content': [ - (r'<\s*/\s*html\s*>', Name.Tag, '#pop'), + (r'<\s*/\s*html\s*>"', Name.Tag, '#pop'), (r'.+?(?=<\s*/\s*html\s*>)', using(HtmlLexer)), ] } @@ -1381,9 +1386,9 @@ class RebolLexer(RegexLexer): tokens = { 'root': [ - (r'REBOL', Generic.Strong, 'script'), - (r'R', Comment), (r'[^R]+', Comment), + (r'REBOL\s+\[', Generic.Strong, 'script'), + (r'R', Comment) ], 'script': [ (r'\s+', Text), @@ -1400,8 +1405,8 @@ class RebolLexer(RegexLexer): (r'%[^(\^{^")\s\[\]]+', Name.Decorator), (r'[+-]?([a-zA-Z]{1,3})?\$\d+(\.\d+)?', Number.Float), # money (r'[+-]?\d+\:\d+(\:\d+)?(\.\d+)?', String.Other), # time - (r'\d+\-[0-9a-zA-Z]+\-\d+(\/\d+\:\d+(\:\d+)?' - r'([\.\d+]?([+-]?\d+:\d+)?)?)?', String.Other), # date + (r'\d+[\-\/][0-9a-zA-Z]+[\-\/]\d+(\/\d+\:\d+((\:\d+)?' + r'([\.\d+]?([+-]?\d+:\d+)?)?)?)?', String.Other), # date (r'\d+(\.\d+)+\.\d+', Keyword.Constant), # tuple (r'\d+[xX]\d+', Keyword.Constant), # pair (r'[+-]?\d+(\'\d+)?([\.,]\d*)?[eE][+-]?\d+', Number.Float), @@ -1493,6 +1498,16 @@ class RebolLexer(RegexLexer): (r'[^(\[\])]+', Comment), ], } + def analyse_text(text): + """ + Check if code contains REBOL header and so it probably not R code + """ + if re.match(r'^\s*REBOL\s*\[', text, re.IGNORECASE): + # The code starts with REBOL header + return 1.0 + elif re.search(r'\s*REBOL\s*[', text, re.IGNORECASE): + # The code contains REBOL header but also some text before it + return 0.5 class ABAPLexer(RegexLexer): @@ -1680,6 +1695,7 @@ class ABAPLexer(RegexLexer): # because < and > are part of field symbols. (r'[?*<>=\-+]', Operator), (r"'(''|[^'])*'", String.Single), + (r"`([^`])*`", String.Single), (r'[/;:()\[\],\.]', Punctuation) ], } @@ -1780,6 +1796,7 @@ class GherkinLexer(RegexLexer): 'examples_table_header': [ (r"\s+\|\s*$", Keyword, "#pop:2"), include('comments'), + (r"\\\|", Name.Variable), (r"\s*\|", Keyword), (r"[^\|]", Name.Variable), ], @@ -1822,6 +1839,7 @@ class GherkinLexer(RegexLexer): 'table_content': [ (r"\s+\|\s*$", Keyword, "#pop"), include('comments'), + (r"\\\|", String), (r"\s*\|", Keyword), include('string'), ], diff --git a/pygments/lexers/web.py b/pygments/lexers/web.py index 142fef57..b0c5d4b7 100644 --- a/pygments/lexers/web.py +++ b/pygments/lexers/web.py @@ -833,7 +833,8 @@ class PhpLexer(RegexLexer): r'endif|list|__LINE__|endswitch|new|__sleep|endwhile|not|' r'array|__wakeup|E_ALL|NULL|final|php_user_filter|interface|' r'implements|public|private|protected|abstract|clone|try|' - r'catch|throw|this|use|namespace|trait)\b', Keyword), + r'catch|throw|this|use|namespace|trait|yield|' + r'finally)\b', Keyword), (r'(true|false|null)\b', Keyword.Constant), (r'\$\{\$+[a-zA-Z_][a-zA-Z0-9_]*\}', Name.Variable), (r'\$+[a-zA-Z_][a-zA-Z0-9_]*', Name.Variable), @@ -843,6 +844,7 @@ class PhpLexer(RegexLexer): (r'0[0-7]+', Number.Oct), (r'0[xX][a-fA-F0-9]+', Number.Hex), (r'\d+', Number.Integer), + (r'0b[01]+', Number.Binary), (r"'([^'\\]*(?:\\.[^'\\]*)*)'", String.Single), (r'`([^`\\]*(?:\\.[^`\\]*)*)`', String.Backtick), (r'"', String.Double, 'string'), @@ -2442,10 +2444,10 @@ class CoffeeScriptLexer(RegexLexer): #(r'^(?=\s|/|<!--)', Text, 'slashstartsregex'), include('commentsandwhitespace'), (r'\+\+|~|&&|\band\b|\bor\b|\bis\b|\bisnt\b|\bnot\b|\?|:|' - r'\|\||\\(?=\n)|(<<|>>>?|==?|!=?|' - r'=(?!>)|-(?!>)|[<>+*`%&\|\^/])=?', + r'\|\||\\(?=\n)|' + r'(<<|>>>?|==?(?!>)|!=?|=(?!>)|-(?!>)|[<>+*`%&\|\^/])=?', Operator, 'slashstartsregex'), - (r'(?:\([^()]+\))?\s*[=-]>', Name.Function), + (r'(?:\([^()]*\))?\s*[=-]>', Name.Function), (r'[{(\[;,]', Punctuation, 'slashstartsregex'), (r'[})\].]', Punctuation), (r'(?<![\.\$])(for|own|in|of|while|until|' diff --git a/pygments/styles/monokai.py b/pygments/styles/monokai.py index 31dc83b2..7b41b3ec 100644 --- a/pygments/styles/monokai.py +++ b/pygments/styles/monokai.py @@ -93,14 +93,14 @@ class MonokaiStyle(Style): String.Symbol: "", # class: 'ss' Generic: "", # class: 'g' - Generic.Deleted: "", # class: 'gd', + Generic.Deleted: "#f92672", # class: 'gd', Generic.Emph: "italic", # class: 'ge' Generic.Error: "", # class: 'gr' Generic.Heading: "", # class: 'gh' - Generic.Inserted: "", # class: 'gi' + Generic.Inserted: "#a6e22e", # class: 'gi' Generic.Output: "", # class: 'go' Generic.Prompt: "", # class: 'gp' Generic.Strong: "bold", # class: 'gs' - Generic.Subheading: "", # class: 'gu' + Generic.Subheading: "#75715e", # class: 'gu' Generic.Traceback: "", # class: 'gt' } |